INDEX

Explanations

phrases related to being accompanied by someone or something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the presence of accompanying or joining entities or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Origin

-0.66

 comprom

-0.61

 RELE

-0.58

urai

-0.58

oro

-0.58

ouf

-0.56

ahime

-0.54

awar

-0.53

 Doctrine

-0.52

 Radius

-0.51

POSITIVE LOGITS

by

1.40

by

1.25

By

1.02

BY

0.95

bys

0.93

By

0.88

Ń·

0.81

BY

0.75

rius

0.75

uated

0.74

Activations Density 0.165%

phrases related to being accompanied by someone or something

phrases indicating the presence of accompanying or joining entities or actions

No Comments

No Known Activations