INDEX

Explanations

verbs related to giving or granting permission

oai_token-act-pair · gpt-3.5-turbo

the word "issue" 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 @ 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

asia

-0.80

bered

-0.78

uton

-0.76

tes

-0.75

 destro

-0.73

bsite

-0.73

sle

-0.72

uphem

-0.70

ombo

-0.69

apy

-0.68

POSITIVE LOGITS

 certificates

0.75

 advis

0.75

 citations

0.74

iates

0.73

 refunds

0.71

iate

0.69

iating

0.66

 rulings

0.66

 forth

0.64

 Statement

0.64

Activations Density 0.032%

verbs related to giving or granting permission

the word "issue" in various contexts

No Comments

No Known Activations