INDEX

Explanations

computer-related terms or commands

oai_token-act-pair · gpt-3.5-turbo

colons followed by lists or items

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

 tremend

-0.82

uve

-0.82

undai

-0.81

mble

-0.76

 inward

-0.72

inement

-0.72

dinand

-0.71

 behavi

-0.71

 behav

-0.70

Initialized

-0.70

POSITIVE LOGITS

 Provided

0.95

TBD

0.88

 Various

0.84

 Cosponsors

0.78

 Beginning

0.77

 https

0.75

 Measures

0.75

Who

0.75

 Introduced

0.74

 Join

0.74

Activations Density 0.109%

computer-related terms or commands

colons followed by lists or items

No Comments

No Known Activations