INDEX

Explanations

words related to "Cerro Paranal" or names containing "Cer" such as "Cecilia" or "Ceramics"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Cerberus" or related keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Buffett

-0.78

ãĥĥãĥĪ

-0.73

 Barkley

-0.71

achusetts

-0.71

lihood

-0.70

sight

-0.67

edit

-0.66

urst

-0.65

 Newsweek

-0.65

share

-0.64

POSITIVE LOGITS

idian

1.02

amic

0.94

Cer

0.93

isine

0.91

oder

0.88

ately

0.86

osa

0.84

acies

0.84

vette

0.81

oding

0.80

Activations Density 0.009%

words related to "Cerro Paranal" or names containing "Cer" such as "Cecilia" or "Ceramics"

references to the term "Cerberus" or related keywords

No Comments

No Known Activations