INDEX

Explanations

abbreviations or acronyms followed by numerical values

oai_token-act-pair · gpt-3.5-turbo

instances of the term "OT," indicating a focus on specific operational terminology or acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

uckland

-0.71

bler

-0.70

 fixme

-0.66

ãĥĭ

-0.62

kers

-0.60

fold

-0.60

 versa

-0.59

TextColor

-0.59

 Thur

-0.59

 afore

-0.59

POSITIVE LOGITS

assium

1.15

TL

1.03

OGR

0.95

TE

0.94

OT

0.93

ECH

0.93

ALS

0.90

uning

0.89

TO

0.87

inyl

0.87

Activations Density 0.012%

abbreviations or acronyms followed by numerical values

instances of the term "OT," indicating a focus on specific operational terminology or acronyms

No Comments

No Known Activations