INDEX

Explanations

phrases or words related to career or profession

oai_token-act-pair · gpt-3.5-turbo

words related to caregiving and care professions

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

 Sanford

-0.67

Geo

-0.66

 rods

-0.65

 Bundy

-0.64

ãĥĻ

-0.63

IVES

-0.63

Yan

-0.62

racuse

-0.61

apo

-0.61

PIT

-0.61

POSITIVE LOGITS

acia

0.76

mma

0.73

quartered

0.73

 counseling

0.72

 Profession

0.71

ploma

0.70

ocratic

0.69

llah

0.68

 endorsements

0.67

 diplomat

0.67

Activations Density 0.033%

phrases or words related to career or profession

words related to caregiving and care professions

No Comments

No Known Activations