INDEX

Explanations

advertisements in the text

oai_token-act-pair · gpt-3.5-turbo

instances of advertisements

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

assic

-0.80

 resultant

-0.69

 masse

-0.68

 helicop

-0.68

 gorilla

-0.67

 apex

-0.67

 tant

-0.66

 destruct

-0.66

stood

-0.65

 embark

-0.65

POSITIVE LOGITS

arty

0.86

edIn

0.81

edin

0.78

rences

0.78

yip

0.77

 ILCS

0.77

ences

0.76

eatures

0.75

Comments

0.75

ROR

0.72

Activations Density 0.016%

advertisements in the text

instances of advertisements

No Comments

No Known Activations