INDEX

Explanations

participants in various experiments or studies

oai_token-act-pair · gpt-3.5-turbo

references to study participants

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

vell

-0.69

 vengeance

-0.66

 Bale

-0.58

 Sense

-0.57

 thicker

-0.57

 clich

-0.56

 Hills

-0.55

stones

-0.55

Rim

-0.55

 Sect

-0.54

POSITIVE LOGITS

cript

0.89

 Participants

0.78

essee

0.77

particip

0.74

hips

0.73

IAL

0.72

uates

0.70

hip

0.70

ividual

0.70

 participant

0.69

Activations Density 0.029%

participants in various experiments or studies

references to study participants

No Comments

No Known Activations