INDEX

Explanations

the term "given", used in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases that include the term "given" in various 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

keepers

-0.83

IDS

-0.76

atis

-0.76

oil

-0.76

quished

-0.73

HUD

-0.72

BIL

-0.72

prints

-0.72

Clar

-0.72

hell

-0.71

POSITIVE LOGITS

 whim

0.76

 sized

0.74

 location

0.74

 individual

0.74

 amount

0.72

 quarter

0.72

 utter

0.69

 tense

0.67

 weight

0.66

 piece

0.66

Activations Density 0.019%

the term "given", used in various contexts

phrases that include the term "given" in various contexts

No Comments

No Known Activations