INDEX

Explanations

names of political figures or personalities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals associated with political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

creen

-0.87

spring

-0.85

lite

-0.70

ModLoader

-0.69

veland

-0.68

wives

-0.66

ura

-0.65

ĪĴ

-0.65

FontSize

-0.64

UAL

-0.63

POSITIVE LOGITS

 Hebdo

0.92

itri

0.79

 Pascal

0.76

theless

0.74

illian

0.71

 Grimm

0.70

opoulos

0.70

aston

0.69

 Damian

0.68

 Luxem

0.68

Activations Density 0.023%

names of political figures or personalities

proper nouns, particularly names of individuals associated with political contexts

No Comments

No Known Activations