INDEX

Explanations

proper nouns related to a specific name, "Dem"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Democrat" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

WAYS

-1.00

renheit

-0.73

DAY

-0.69

CLASSIFIED

-0.68

glers

-0.68

ties

-0.67

Pull

-0.66

OUP

-0.66

=~=~

-0.66

waters

-0.66

POSITIVE LOGITS

olition

1.17

agogue

1.08

agog

0.96

eanor

0.95

psey

0.91

ocrat

0.91

ecast

0.90

otion

0.88

arat

0.87

aterial

0.86

Activations Density 0.009%

proper nouns related to a specific name, "Dem"

mentions of the term "Democrat" in various contexts

No Comments

No Known Activations