INDEX

Explanations

phrases related to political discourse and tax issues

oai_token-act-pair · gpt-3.5-turbo

phrases related to political statements and fairness in the political system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

pmwiki

-0.90

WARE

-0.82

âĹ¼

-0.76

 largeDownload

-0.76

hend

-0.74

agues

-0.73

ufact

-0.72

uthor

-0.71

nil

-0.70

artney

-0.69

POSITIVE LOGITS

 Kavanaugh

1.00

 Dems

0.92

DNC

0.78

']

0.78

 Rosenstein

0.76

 Blumenthal

0.75

 Pelosi

0.75

 Schumer

0.75

 Biden

0.75

 Vote

0.74

Activations Density 0.041%

phrases related to political discourse and tax issues

phrases related to political statements and fairness in the political system

No Comments

No Known Activations