INDEX

Explanations

the name "Watson"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Watson"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

amera

-0.85

ĩ

-0.73

ulatory

-0.68

sters

-0.64

eways

-0.64

uation

-0.63

tera

-0.63

egal

-0.62

stery

-0.62

 fertile

-0.62

POSITIVE LOGITS

atson

1.09

 Watson

1.09

 Holmes

0.83

batch

0.80

 Norton

0.78

orld

0.74

ITNESS

0.72

ITH

0.72

combe

0.71

iband

0.69

Activations Density 0.064%

the name "Watson"

references to the name "Watson"

No Comments

No Known Activations