INDEX

Explanations

locations or geographical names

oai_token-act-pair · gpt-3.5-turbo

references to specific locations, particularly countries or regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

enegger

-1.04

hire

-0.85

 antioxid

-0.75

ollow

-0.75

ancies

-0.74

sonian

-0.74

alez

-0.73

avorite

-0.72

 behav

-0.71

inning

-0.71

POSITIVE LOGITS

 Liberia

1.18

ican

0.79

 Laos

0.79

 Libya

0.78

 Somalia

0.76

ica

0.75

 Tripoli

0.75

 Latvia

0.75

 Mongolia

0.74

 Zamb

0.74

Activations Density 0.012%

locations or geographical names

references to specific locations, particularly countries or regions

No Comments

No Known Activations