INDEX

Explanations

information about eligibility for various benefits or activities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate eligibility for programs, benefits, or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ĸļ

-0.75

ijk

-0.70

 Coat

-0.69

pread

-0.65

Else

-0.64

hed

-0.62

 vengeance

-0.61

birth

-0.60

 incess

-0.60

il

-0.59

POSITIVE LOGITS

untarily

0.86

iaries

0.83

itable

0.80

mma

0.78

igible

0.78

iary

0.76

itably

0.73

irements

0.73

asma

0.71

lig

0.71

Activations Density 0.021%

information about eligibility for various benefits or activities

phrases that indicate eligibility for programs, benefits, or services

No Comments

No Known Activations