INDEX

Explanations

phrases expressing a positive or negative evaluation or sentiment

oai_token-act-pair · gpt-3.5-turbo

the presence of the pronoun "it" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

wcsstore

-0.68

 Greens

-0.62

 Cards

-0.58

 Politics

-0.56

 Disabled

-0.56

 Nationals

-0.55

 Pirates

-0.54

 Instruments

-0.54

 Jacksonville

-0.54

 Coalition

-0.53

POSITIVE LOGITS

alian

1.51

chy

1.24

atic

1.21

self

1.17

unes

1.00

atically

0.96

atics

0.84

asca

0.82

selves

0.78

alia

0.78

Activations Density 0.141%

phrases expressing a positive or negative evaluation or sentiment

the presence of the pronoun "it" in various contexts

No Comments

No Known Activations