INDEX

Explanations

the word "attitude" with different contexts and intensities

oai_token-act-pair · gpt-3.5-turbo

recurring themes related to attitudes or beliefs

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

enegger

-1.01

icles

-0.92

oval

-0.80

icle

-0.76

aneously

-0.74

icular

-0.73

eri

-0.71

ÄŁ

-0.70

iaries

-0.70

lisher

-0.68

POSITIVE LOGITS

 attitude

1.15

 toward

1.12

 towards

1.07

 attitudes

0.89

 Towards

0.84

Tow

0.76

ysis

0.75

uation

0.73

 perv

0.71

 indifference

0.71

Activations Density 0.023%

the word "attitude" with different contexts and intensities

recurring themes related to attitudes or beliefs

No Comments

No Known Activations