INDEX

Explanations

keywords within a coding context

oai_token-act-pair · gpt-3.5-turbo

occurrences of opening parentheses in the text

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

 USAF

-0.65

orate

-0.65

 Nunes

-0.64

Kin

-0.64

 Hemisphere

-0.64

 Chak

-0.63

 Kear

-0.62

RC

-0.61

 Marble

-0.60

 Shiva

-0.60

POSITIVE LOGITS

catentry

1.01

wcsstore

0.87

tnc

0.79

onduct

0.77

rag

0.74

acho

0.73

stuff

0.73

artifacts

0.72

pret

0.71

borgh

0.70

Activations Density 0.023%

keywords within a coding context

occurrences of opening parentheses in the text

No Comments

No Known Activations