INDEX

Explanations

phrases related to corporate punishment or policies

oai_token-act-pair · gpt-3.5-turbo

references to corporate punishment and related discussions

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

draft

-0.76

WAYS

-0.75

BOOK

-0.67

infeld

-0.67

 Secrets

-0.66

Discover

-0.66

finding

-0.66

 Passage

-0.66

brates

-0.65

forcing

-0.65

POSITIVE LOGITS

 corpor

1.03

ately

0.97

atis

0.96

 mathemat

0.94

acies

0.94

uitous

0.93

iple

0.91

abulary

0.88

ateurs

0.86

ãĤ¼ãĤ¦ãĤ¹

0.84

Activations Density 0.017%

phrases related to corporate punishment or policies

references to corporate punishment and related discussions

No Comments

No Known Activations