INDEX

Explanations

names of influential persons, such as leaders, revolutionaries, and figures in various fields

oai_token-act-pair · gpt-3.5-turbo

nouns related to leadership and influential figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ciplinary

-0.73

erial

-0.72

 differed

-0.71

cffffcc

-0.71

isoft

-0.70

 confir

-0.69

MpServer

-0.67

aber

-0.66

 clutch

-0.65

ivable

-0.64

POSITIVE LOGITS

 Stephen

1.02

 Nathan

1.00

 Steve

1.00

 Tony

1.00

 Gina

1.00

 David

1.00

 Robert

0.99

 Bruce

0.97

 Andrew

0.96

 Larry

0.96

Activations Density 0.333%

names of influential persons, such as leaders, revolutionaries, and figures in various fields

nouns related to leadership and influential figures

No Comments

No Known Activations