INDEX

Explanations

geographical locations, specifically cities and regions

oai_token-act-pair · gpt-3.5-turbo

city names and locations related to news articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Gamble

-0.71

 Lomb

-0.70

 Cipher

-0.69

 Loft

-0.68

 Lieberman

-0.67

 Verb

-0.65

 Clapper

-0.65

 Birch

-0.64

 Priv

-0.63

 Staten

-0.63

POSITIVE LOGITS

ION

0.93

IONS

0.90

URA

0.83

 CITY

0.81

IVERS

0.80

ENN

0.80

ANA

0.80

ANCE

0.79

ES

0.79

ARY

0.78

Activations Density 0.051%

geographical locations, specifically cities and regions

city names and locations related to news articles

No Comments

No Known Activations