INDEX

Explanations

phrases related to political discussions and actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating opposition or disagreement related to legislation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 realised

-1.05

 realise

-1.04

 learnt

-0.88

 Whilst

-0.86

:-)

-0.83

 labou

-0.82

 å¤

-0.82

Firstly

-0.79

 ðŁĻĤ

-0.78

 civilisation

-0.78

POSITIVE LOGITS

 congressional

1.44

 Gorsuch

1.39

 ObamaCare

1.37

 DeVos

1.32

 filibuster

1.32

 Comey

1.32

 Kavanaugh

1.31

 Trump

1.31

 Senate

1.30

 Hillary

1.29

Activations Density 0.837%

phrases related to political discussions and actions

phrases indicating opposition or disagreement related to legislation

No Comments

No Known Activations