INDEX

Explanations

phrases related to economic or political discussions

oai_token-act-pair · gpt-3.5-turbo

phrases related to services or offerings

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

 Herz

-0.68

 Steel

-0.66

chio

-0.66

 Camp

-0.63

 Blanc

-0.62

âĨĳ

-0.62

 Government

-0.61

 Wright

-0.61

lest

-0.61

 Administration

-0.61

POSITIVE LOGITS

 ende

0.97

 skelet

0.88

 incorpor

0.88

isphere

0.82

ktop

0.81

 incent

0.75

 notor

0.75

perty

0.74

 streng

0.72

 resil

0.72

Activations Density 0.000%

phrases related to economic or political discussions

phrases related to services or offerings

No Comments

No Known Activations