INDEX

Explanations

references to cars

oai_token-act-pair · gpt-3.5-turbo

references to cars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Flavoring

-0.88

 Seym

-0.85

edIn

-0.75

ollah

-0.75

scl

-0.74

 Lans

-0.74

xual

-0.73

EngineDebug

-0.73

 Dull

-0.72

iversal

-0.71

POSITIVE LOGITS

ousel

1.55

riages

1.37

penter

1.37

rera

1.13

olina

1.03

riage

1.03

 dealership

0.97

negie

0.94

avan

0.93

abin

0.93

Activations Density 0.046%

references to cars

references to cars

No Comments

No Known Activations