INDEX

Explanations

words related to political entities or movements, such as names of political figures or organizations

oai_token-act-pair · gpt-3.5-turbo

variations of the word "em."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Kubrick

-0.65

bed

-0.64

 Rockies

-0.64

SourceFile

-0.63

 Toad

-0.60

 steroids

-0.56

 obsc

-0.56

 Walters

-0.56

 Mighty

-0.56

 Encyclopedia

-0.56

POSITIVE LOGITS

issions

1.23

peror

1.19

achine

1.18

otional

1.14

bley

1.09

bourg

1.08

phasis

1.07

useum

1.07

ple

1.07

igrant

1.05

Activations Density 0.030%

words related to political entities or movements, such as names of political figures or organizations

variations of the word "em."

No Comments

No Known Activations