INDEX

Explanations

references to cultural aspects or elements specifically

oai_token-act-pair · gpt-3.5-turbo

references to cultural concepts and phenomena

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

redd

-0.80

ded

-0.79

lain

-0.78

ding

-0.76

etsk

-0.75

ldon

-0.74

alos

-0.74

ym

-0.73

reens

-0.72

umbn

-0.72

POSITIVE LOGITS

 heritage

1.00

ultural

0.93

 cultural

0.92

 arte

0.88

 Marxism

0.88

 appropriation

0.88

 norms

0.86

 attractions

0.84

 Cultural

0.84

cultural

0.83

Activations Density 0.014%

references to cultural aspects or elements specifically

references to cultural concepts and phenomena

No Comments

No Known Activations