INDEX

Explanations

images or captions marked for enlargement on documents

oai_token-act-pair · gpt-3.5-turbo

instances of prompts to enlarge images or toggle elements in the document

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

comes

-0.71

stood

-0.67

anger

-0.65

population

-0.61

meal

-0.61

shall

-0.61

dies

-0.61

rams

-0.60

 sacrific

-0.59

agall

-0.59

POSITIVE LOGITS

Enlarge

1.08

 WATCHED

0.93

UTERS

0.80

ONSORED

0.78

 Thumbnails

0.73

 toggle

0.72

 caption

0.72

 "$:/

0.71

 captcha

0.70

 Reached

0.68

Activations Density 0.008%

images or captions marked for enlargement on documents

instances of prompts to enlarge images or toggle elements in the document

No Comments

No Known Activations