INDEX

Explanations

words related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and significant entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 unison

-0.64

 Jupiter

-0.62

Reloaded

-0.60

awaru

-0.59

 Dynamo

-0.59

 horizont

-0.58

 novelty

-0.57

 Kurd

-0.57

 Toad

-0.56

 Galile

-0.56

POSITIVE LOGITS

lance

0.89

oub

0.87

bernatorial

0.82

reach

0.78

mbudsman

0.78

guards

0.76

wings

0.75

ainer

0.75

itions

0.75

ress

0.72

Activations Density 0.463%

words related to geographical locations

proper nouns and significant entities

No Comments

No Known Activations