INDEX

Explanations

mentions of schemes or programs

oai_token-act-pair · gpt-3.5-turbo

references to various schemes or programs

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

Flo

-0.68

 Clover

-0.64

ãģĹ

-0.62

Heat

-0.60

Nob

-0.60

Hug

-0.59

inas

-0.59

cknowled

-0.58

 Hond

-0.58

Rated

-0.57

POSITIVE LOGITS

 scheme

1.09

 schemes

1.07

ulence

0.87

eers

0.86

ĸļ

0.86

eering

0.83

etary

0.82

 devised

0.81

 Scheme

0.74

matic

0.74

Activations Density 0.014%

mentions of schemes or programs

references to various schemes or programs

No Comments

No Known Activations