INDEX

Explanations

proper nouns related to academic institutions

oai_token-act-pair · gpt-3.5-turbo

references to academic institutions and organizations

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

swing

-0.86

uel

-0.83

gers

-0.78

ĪĴ

-0.73

UE

-0.73

matter

-0.72

rx

-0.71

ged

-0.69

edit

-0.69

selection

-0.69

POSITIVE LOGITS

 Mellon

1.29

 Institution

1.21

negie

1.14

 Carnegie

0.94

 Institutes

0.79

kefeller

0.78

myra

0.72

 Instit

0.71

 Bernstein

0.69

©¶æ¥µ

0.68

Activations Density 0.010%

proper nouns related to academic institutions

references to academic institutions and organizations

No Comments

No Known Activations