INDEX

Explanations

adjectives related to behavior or personality traits

oai_token-act-pair · gpt-3.5-turbo

words related to strong warnings or admonitions

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

Downloadha

-0.88

akeru

-0.81

ETF

-0.78

RESULTS

-0.73

iphate

-0.73

Winner

-0.71

Journal

-0.68

WAYS

-0.66

journal

-0.65

xtap

-0.65

POSITIVE LOGITS

 stern

0.97

ly

0.95

 rebuke

0.83

 discipl

0.78

gest

0.78

 reprim

0.76

unci

0.74

faced

0.73

stem

0.72

 demeanor

0.72

Activations Density 0.013%

adjectives related to behavior or personality traits

words related to strong warnings or admonitions

No Comments

No Known Activations