INDEX

Explanations

phrases related to political events or actions involving Republicans

oai_token-act-pair · gpt-3.5-turbo

references to political parties and their actions in Congress

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 labou

-0.77

autical

-0.68

 cowork

-0.68

 childbirth

-0.66

 visitation

-0.65

 paramed

-0.64

 corpus

-0.63

 Happiness

-0.63

 inhal

-0.62

obar

-0.62

POSITIVE LOGITS

 majorities

1.01

Republicans

1.00

 partisans

1.00

Democrats

0.97

ervatives

0.89

 centr

0.87

 defund

0.84

 politic

0.84

 Caucus

0.83

 Flake

0.82

Activations Density 0.502%

phrases related to political events or actions involving Republicans

references to political parties and their actions in Congress

No Comments

No Known Activations