INDEX

Explanations

references to political figures and positions within a specific political party

oai_token-act-pair · gpt-3.5-turbo

references to political figures and their roles or actions

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

heid

-0.85

Vu

-0.85

 Amsterdam

-0.79

 Torres

-0.77

 apartheid

-0.77

Gaza

-0.77

ibaba

-0.76

Ng

-0.76

ijk

-0.76

 Mata

-0.74

POSITIVE LOGITS

 Boehner

1.61

GOP

1.47

GOP

1.35

Republicans

1.30

RNC

1.29

 Corker

1.28

 Republican

1.25

 McConnell

1.24

Republican

1.23

 House

1.23

Activations Density 0.378%

references to political figures and positions within a specific political party

references to political figures and their roles or actions

No Comments

No Known Activations