INDEX

Explanations

technical terms related to computer programming and documentation within text

oai_token-act-pair · gpt-3.5-turbo

terms associated with categorization or classification, particularly in technical, legal, and political contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istries

-0.86

 partName

-0.79

abases

-0.72

edin

-0.71

tern

-0.69

merce

-0.68

âĿ

-0.67

xus

-0.65

 Unreal

-0.64

uncture

-0.63

POSITIVE LOGITS

 progresses

1.00

 ascended

0.75

 progressed

0.71

 navig

0.70

 identifiers

0.68

 enters

0.67

 standalone

0.65

 divid

0.64

 witnesses

0.63

 interven

0.63

Activations Density 0.287%

technical terms related to computer programming and documentation within text

terms associated with categorization or classification, particularly in technical, legal, and political contexts

No Comments

No Known Activations