INDEX

Explanations

countries or locations

oai_token-act-pair · gpt-3.5-turbo

mentions of geographical locations or regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 deed

-0.70

itus

-0.70

natureconservancy

-0.69

 impedance

-0.67

 deeds

-0.65

¬¼

-0.65

orph

-0.63

raph

-0.63

rive

-0.63

issance

-0.62

POSITIVE LOGITS

England

1.05

where

1.00

 Netherlands

0.95

 Belgium

0.95

 where

0.95

 England

0.93

 Chile

0.90

 Colombia

0.90

 Siberia

0.90

 France

0.89

Activations Density 0.278%

countries or locations

mentions of geographical locations or regions

No Comments

No Known Activations