INDEX

Explanations

terms related to influential factors or components

oai_token-act-pair · gpt-3.5-turbo

references to contributing factors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

gem

-0.81

alach

-0.78

phis

-0.74

©¶æ

-0.74

 Chaser

-0.74

 Seym

-0.72

ichick

-0.72

oÄŁ

-0.72

escription

-0.71

quartered

-0.70

POSITIVE LOGITS

 factors

0.99

 Factors

0.86

factor

0.83

 factor

0.82

 influencing

0.81

 affecting

0.78

 contributing

0.76

iator

0.71

 determines

0.71

 aggrav

0.71

Activations Density 0.033%

terms related to influential factors or components

references to contributing factors in various contexts

No Comments

No Known Activations