INDEX

Explanations

images with captions

oai_token-act-pair · gpt-3.5-turbo

the word "this"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Sword

-0.67

NAS

-0.67

APD

-0.66

 Vand

-0.66

ORED

-0.65

 Nadu

-0.65

Sund

-0.65

 Rounds

-0.65

uality

-0.64

POSITIVE LOGITS

 toggle

0.87

 WATCHED

0.77

 image

0.74

 CASE

0.73

 transcript

0.73

 month

0.72

ebin

0.72

 ARTICLE

0.71

 page

0.69

 slide

0.68

Activations Density 0.020%

images with captions

the word "this"

No Comments

No Known Activations