INDEX

Explanations

references to folk-related content

oai_token-act-pair · gpt-3.5-turbo

references to folk music or folk culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

xus

-0.77

Effective

-0.71

lain

-0.68

xual

-0.63

 Rack

-0.60

isites

-0.60

 barrel

-0.59

 Effective

-0.59

 Higgins

-0.59

 funnel

-0.59

POSITIVE LOGITS

lore

1.31

lor

1.17

tale

1.15

folk

1.15

endor

0.92

 tales

0.92

estone

0.91

worker

0.91

mere

0.90

 tale

0.82

Activations Density 0.022%

references to folk-related content

references to folk music or folk culture

No Comments

No Known Activations