INDEX

Explanations

references to the United Nations (UN)

oai_token-act-pair · gpt-3.5-turbo

the presence of references to the United Nations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Feldman

-0.72

 conservatism

-0.69

 constituency

-0.65

 fascism

-0.65

 shave

-0.62

 goodbye

-0.62

 Slate

-0.62

laz

-0.62

 everything

-0.61

Sel

-0.61

POSITIVE LOGITS

UN

4.08

UNE

1.91

UN

1.78

un

1.65

uns

1.59

UNCH

1.39

UL

1.39

unt

1.38

UM

1.35

OU

1.34

Activations Density 0.011%

references to the United Nations (UN)

the presence of references to the United Nations

No Comments

No Known Activations