INDEX

Explanations

countries or nationalities associated with North Africa

oai_token-act-pair · gpt-3.5-turbo

references to Tunisia and related geographical or national entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bilt

-0.88

alach

-0.83

lasses

-0.82

ving

-0.79

rint

-0.78

croft

-0.77

effic

-0.74

loss

-0.73

rising

-0.71

isner

-0.69

POSITIVE LOGITS

 Tunis

1.00

 Tunisia

0.96

 Tanz

0.88

 Airways

0.78

ophobia

0.75

etta

0.72

 RÃ©

0.72

ophobic

0.72

 Mubarak

0.72

Reloaded

0.70

Activations Density 0.015%

countries or nationalities associated with North Africa

references to Tunisia and related geographical or national entities

No Comments

No Known Activations