INDEX

Explanations

the word "chess"

oai_token-act-pair · gpt-3.5-turbo

references to chess and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igious

-0.77

uated

-0.76

ient

-0.75

 unnamed

-0.75

aneous

-0.74

ibus

-0.71

ufact

-0.71

aneously

-0.68

uating

-0.66

 OPEC

-0.65

POSITIVE LOGITS

 chess

1.11

 Chess

0.96

 rook

0.87

 puzzles

0.83

 Solitaire

0.82

bowl

0.81

pai

0.80

manship

0.80

cube

0.78

 puzzle

0.77

Activations Density 0.012%

the word "chess"

references to chess and related activities

No Comments

No Known Activations