INDEX

Explanations

proper names or organizations being in a leading position

oai_token-act-pair · gpt-3.5-turbo

phrases indicating leadership or groups being led

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Leilan

-0.65

 comfort

-0.62

 Showdown

-0.59

issues

-0.57

 Crash

-0.56

 DISTR

-0.56

irlf

-0.56

 srfAttach

-0.54

 redundancy

-0.54

 McCorm

-0.54

POSITIVE LOGITS

gers

1.05

by

1.01

ges

0.97

by

0.92

gling

0.86

ger

0.84

ging

0.83

bys

0.83

ged

0.82

eric

0.82

Activations Density 0.055%

proper names or organizations being in a leading position

phrases indicating leadership or groups being led

No Comments

No Known Activations