INDEX

Explanations

phrases related to comments or observations made by individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "remark" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 conflic

-0.69

 inhibitors

-0.67

href

-0.65

testers

-0.62

ccording

-0.62

AAF

-0.62

 fronts

-0.60

 inhibitor

-0.59

driving

-0.59

addy

-0.59

POSITIVE LOGITS

ury

0.81

eteenth

0.80

 sarcast

0.79

ufact

0.78

ault

0.77

 upon

0.76

tainment

0.74

 bour

0.73

geist

0.73

iasis

0.72

Activations Density 0.075%

phrases related to comments or observations made by individuals

instances of the word "remark" and its variations

No Comments

No Known Activations