INDEX

Explanations

references to geographical locations or entities that include the word "North" in them

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly geographical and organizational names

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

iasco

-0.73

 Archdemon

-0.71

=-=-=-=-

-0.68

ocument

-0.67

initialized

-0.64

Wan

-0.64

Related

-0.61

cellent

-0.61

thood

-0.61

 certific

-0.60

POSITIVE LOGITS

roth

0.78

 Abbey

0.70

landers

0.69

iever

0.68

oway

0.67

ukong

0.65

church

0.64

dden

0.62

 Slov

0.61

acher

0.60

Activations Density 0.132%

references to geographical locations or entities that include the word "North" in them

proper nouns, particularly geographical and organizational names

No Comments

No Known Activations