INDEX

Explanations

proper nouns related to specific geographical regions or organizations

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations or areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

pmwiki

-0.83

ulators

-0.74

ulating

-0.72

eren

-0.69

TIME

-0.68

ersed

-0.67

uous

-0.67

stra

-0.66

oldown

-0.66

ulatory

-0.64

POSITIVE LOGITS

 Than

0.93

 Greater

0.85

Mek

0.84

 Manchester

0.83

 Lansing

0.79

 Albania

0.78

 Cincinnati

0.76

 Yellowstone

0.76

burgh

0.74

 Angeles

0.73

Activations Density 0.040%

proper nouns related to specific geographical regions or organizations

references to geographical locations or areas

No Comments

No Known Activations