INDEX

Explanations

words related to rights, obligations, responsibilities, and moral implications

oai_token-act-pair · gpt-3.5-turbo

references to rights and obligations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

early

-0.64

hooting

-0.62

merce

-0.60

itsch

-0.59

Byr

-0.59

late

-0.59

PF

-0.57

 diligent

-0.57

into

-0.57

steps

-0.56

POSITIVE LOGITS

 knack

0.78

 vested

0.76

ointed

0.66

kees

0.65

 lined

0.63

icum

0.63

say

0.63

Ö¼

0.63

 credibility

0.62

 redeem

0.62

Activations Density 0.247%

words related to rights, obligations, responsibilities, and moral implications

references to rights and obligations in various contexts

No Comments

No Known Activations