INDEX

Explanations

phrases related to official statements or reports

oai_token-act-pair · gpt-3.5-turbo

instances of numerical data and quantitative information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

senal

-0.81

heit

-0.71

awei

-0.66

aeda

-0.57

ļé

-0.57

aturdays

-0.57

anqu

-0.56

culus

-0.56

social

-0.56

ensibly

-0.56

POSITIVE LOGITS

Scroll

0.83

 Related

0.66

 Imran

0.66

 Universities

0.65

 Franch

0.64

 Debor

0.64

SEE

0.63

Ala

0.62

 Reporter

0.62

↵

0.59

Activations Density 0.500%

phrases related to official statements or reports

instances of numerical data and quantitative information

No Comments

No Known Activations