INDEX

Explanations

words related to political contests or rallies

oai_token-act-pair · gpt-3.5-turbo

mentions of "raucous" or related terms referring to loud, boisterous behavior or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Defenders

-0.64

Im

-0.62

senal

-0.59

Assembly

-0.58

 Intercept

-0.58

 image

-0.57

 Fundamental

-0.57

 Proposition

-0.57

doc

-0.57

Hug

-0.57

POSITIVE LOGITS

auc

1.59

umbers

0.93

ilities

0.90

upuncture

0.89

aucuses

0.86

kees

0.84

aucus

0.83

halla

0.81

oup

0.80

aucas

0.79

Activations Density 0.005%

words related to political contests or rallies

mentions of "raucous" or related terms referring to loud, boisterous behavior or events

No Comments

No Known Activations