INDEX

Explanations

references to the Democratic Party

oai_token-act-pair · gpt-3.5-turbo

mentions of the Democratic Party

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

asus

-0.90

paio

-0.81

laus

-0.80

olkien

-0.79

ogie

-0.78

NRS

-0.78

anamo

-0.78

icles

-0.78

 Gutenberg

-0.77

krit

-0.77

POSITIVE LOGITS

 Party

1.08

 frontrunner

0.94

 nominee

0.93

 stronghold

0.87

 Republic

0.86

 presidential

0.85

 hopeful

0.84

 caucuses

0.84

 strongh

0.83

 operative

0.80

Activations Density 0.032%

references to the Democratic Party

mentions of the Democratic Party

No Comments

No Known Activations