INDEX

Explanations

references to the country of Thailand

oai_token-act-pair · gpt-3.5-turbo

references to Thailand and its associated cultural descriptors

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ships

-0.85

 Lazarus

-0.80

eer

-0.79

pring

-0.78

bolt

-0.72

ellen

-0.71

Ö¼

-0.70

BAT

-0.69

bre

-0.69

 Crow

-0.69

POSITIVE LOGITS

ailand

0.96

 Airways

0.83

arma

0.80

ulhu

0.79

 clinch

0.79

uran

0.78

ractor

0.76

isma

0.76

nown

0.76

gum

0.74

Activations Density 0.016%

references to the country of Thailand

references to Thailand and its associated cultural descriptors

No Comments

No Known Activations