INDEX

Explanations

words related to various influencing factors or causes

oai_token-act-pair · gpt-3.5-turbo

references to various external and internal influences or determinants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

alach

-0.84

©¶æ¥µ

-0.79

 Parables

-0.78

geon

-0.76

gem

-0.73

©¶æ

-0.71

rito

-0.70

yright

-0.68

ichick

-0.68

phis

-0.68

POSITIVE LOGITS

 factors

1.13

 Factors

0.95

 affecting

0.87

 variables

0.84

 influencing

0.83

 predis

0.79

 triggers

0.76

 impacting

0.76

 factor

0.76

factor

0.75

Activations Density 0.028%

words related to various influencing factors or causes

references to various external and internal influences or determinants

No Comments

No Known Activations