INDEX

Explanations

proper nouns related to politics and personalities

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or entities linked to a narrative

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

ocal

-0.81

utical

-0.79

ises

-0.77

icate

-0.74

UAL

-0.73

ual

-0.73

icals

-0.72

iary

-0.72

 Mehran

-0.71

ically

-0.70

POSITIVE LOGITS

bench

0.77

noon

0.75

pole

0.74

Stack

0.74

tons

0.73

tail

0.72

butt

0.72

mie

0.72

bra

0.71

ben

0.71

Activations Density 0.028%

proper nouns related to politics and personalities

mentions of specific individuals or entities linked to a narrative

No Comments

No Known Activations