INDEX

Explanations

words related to specific themes or topics

oai_token-act-pair · gpt-3.5-turbo

references to themes in entertainment, particularly related to theme parks

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

rah

-0.88

ards

-0.78

rations

-0.74

rets

-0.73

poons

-0.73

ARD

-0.73

pta

-0.71

lishes

-0.70

aq

-0.69

UGE

-0.69

POSITIVE LOGITS

 theme

1.24

theme

1.07

 themes

1.00

 Theme

0.90

Theme

0.85

ĸļ

0.82

stay

0.81

 rehearsal

0.80

oleon

0.79

 park

0.78

Activations Density 0.009%

words related to specific themes or topics

references to themes in entertainment, particularly related to theme parks

No Comments

No Known Activations