INDEX

Explanations

phrases related to searching or investigating

oai_token-act-pair · gpt-3.5-turbo

references to search operations or efforts

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

ivari

-0.84

minecraft

-0.71

 Leilan

-0.69

Production

-0.68

nect

-0.67

noxious

-0.65

earned

-0.64

 imitation

-0.64

Earn

-0.63

signed

-0.63

POSITIVE LOGITS

 Warrant

0.85

 warrant

0.85

 engines

0.83

 warrants

0.76

prising

0.76

lights

0.75

able

0.74

 engine

0.71

ability

0.70

 Holmes

0.68

Activations Density 0.029%

phrases related to searching or investigating

references to search operations or efforts

No Comments

No Known Activations