INDEX

Explanations

phrases related to holding law enforcement accountable

oai_token-act-pair · gpt-3.5-turbo

instances of empty or whitespace-separated text segments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Government

-0.64

PLIED

-0.64

 Government

-0.63

 Instr

-0.63

Grade

-0.63

 Labor

-0.60

 predec

-0.60

Lot

-0.59

 âĢ¦"

-0.58

 Paraly

-0.57

POSITIVE LOGITS

 Profile

0.86

join

0.82

keyes

0.74

roma

0.72

 english

0.69

hu

0.69

iosis

0.69

dj

0.68

Offline

0.68

wolf

0.68

Activations Density 0.398%

phrases related to holding law enforcement accountable

instances of empty or whitespace-separated text segments

No Comments

No Known Activations