INDEX

Explanations

words related to rules, regulations, or expected behavior

oai_token-act-pair · gpt-3.5-turbo

references to standards of behavior and conduct

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inka

-0.68

iewicz

-0.64

MEN

-0.63

ixed

-0.62

 Nightmares

-0.62

cial

-0.61

 Sanchez

-0.61

 Fried

-0.59

 berth

-0.59

Cec

-0.59

POSITIVE LOGITS

ors

1.03

ivity

1.00

uations

0.94

ities

0.90

onduct

0.89

ional

0.89

uated

0.82

ions

0.80

uation

0.79

ivism

0.77

Activations Density 0.023%

words related to rules, regulations, or expected behavior

references to standards of behavior and conduct

No Comments

No Known Activations