INDEX

Explanations

mentions of cultural aspects or references in the text

oai_token-act-pair · gpt-3.5-turbo

references to culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

heed

-0.75

iary

-0.74

deen

-0.70

ded

-0.67

oug

-0.66

fman

-0.66

ding

-0.66

minster

-0.65

headers

-0.65

 Parenthood

-0.65

POSITIVE LOGITS

 culture

1.00

 Culture

0.96

uria

0.80

 cultures

0.77

ulture

0.73

culture

0.73

 diversity

0.71

 Appropri

0.71

 norms

0.68

lia

0.68

Activations Density 0.013%

mentions of cultural aspects or references in the text

references to culture

No Comments

No Known Activations