INDEX

Explanations

references to locations or geographical territories

oai_token-act-pair · gpt-3.5-turbo

references to geographical or political territories

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

odcast

-0.83

racted

-0.78

oster

-0.78

uster

-0.73

Case

-0.73

uth

-0.71

Bi

-0.70

asting

-0.68

Episode

-0.68

kus

-0.67

POSITIVE LOGITS

 boundaries

0.90

 conquered

0.89

 Territories

0.86

 territory

0.83

 territories

0.83

 Territory

0.79

 inhabited

0.77

 borders

0.77

 bordering

0.76

 sovereignty

0.75

Activations Density 0.025%

references to locations or geographical territories

references to geographical or political territories

No Comments

No Known Activations