INDEX

Explanations

phrases related to introducing topics or transitioning between topics

oai_token-act-pair · gpt-3.5-turbo

references to topics being introduced or discussed

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

prus

-0.80

phia

-0.79

Ctrl

-0.78

æ©

-0.73

eer

-0.71

ĸļ

-0.71

earchers

-0.69

bike

-0.67

opter

-0.66

atra

-0.64

POSITIVE LOGITS

 seriousness

0.64

 specifics

0.64

 matters

0.63

 nutshell

0.63

gin

0.62

 external

0.61

 cases

0.60

 downside

0.60

ado

0.59

wards

0.59

Activations Density 0.092%

phrases related to introducing topics or transitioning between topics

references to topics being introduced or discussed

No Comments

No Known Activations