INDEX

Explanations

phrases indicating that a problem or issue is being discussed or identified

oai_token-act-pair · gpt-3.5-turbo

repeated characters or symbols

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mobil

-0.68

 Colossus

-0.64

 partnerships

-0.63

 Tanz

-0.63

 Siem

-0.63

 barr

-0.61

 bilingual

-0.60

 pulp

-0.58

 scattering

-0.58

 juggling

-0.57

POSITIVE LOGITS

fter

0.85

Pg

0.81

own

0.80

forth

0.80

else

0.79

mir

0.78

tu

0.78

uable

0.78

resh

0.75

aird

0.74

Activations Density 0.077%

phrases indicating that a problem or issue is being discussed or identified

repeated characters or symbols

No Comments

No Known Activations