INDEX

Explanations

references to political processes and legislation

oai_token-act-pair · gpt-3.5-turbo

terms related to legislative processes and bipartisan support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 metab

-0.74

ogy

-0.70

ãĤª

-0.69

agate

-0.69

 Crate

-0.67

voy

-0.67

Desc

-0.67

 Hebdo

-0.66

 Seraph

-0.66

 Desc

-0.65

POSITIVE LOGITS

 unanim

1.60

 unanimous

1.48

 majorities

1.45

 ratification

1.45

 votes

1.45

 bipartisan

1.36

 veto

1.32

votes

1.27

 approval

1.26

 filibuster

1.23

Activations Density 0.483%

references to political processes and legislation

terms related to legislative processes and bipartisan support

No Comments

No Known Activations