INDEX

Explanations

statistics and numerical values

oai_token-act-pair · gpt-3.5-turbo

phrases related to estimates and numerical data

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

ener

-0.72

yles

-0.70

iscover

-0.67

leon

-0.66

eret

-0.65

erton

-0.62

Thumbnail

-0.62

enment

-0.59

ipolar

-0.58

adra

-0.56

POSITIVE LOGITS

 probabilities

0.88

amount

0.84

verages

0.82

pex

0.75

FontSize

0.75

 ceiling

0.74

 projections

0.73

 estimating

0.73

 accuracy

0.71

hiba

0.71

Activations Density 0.240%

statistics and numerical values

phrases related to estimates and numerical data

No Comments

No Known Activations