INDEX

Explanations

addresses or locations in California

oai_token-act-pair · gpt-3.5-turbo

U.S. state abbreviations and their occurrences in text

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

lihood

-0.97

-0.69

ÄŁ

-0.68

ãĤ¨ãĥ«

-0.68

mania

-0.67

Versions

-0.67

Afee

-0.67

andowski

-0.66

ãĥĬ

-0.66

henko

-0.65

POSITIVE LOGITS

 tradem

0.71

UL

0.68

ARA

0.65

hovah

0.64

 Received

0.63

 Supervisor

0.62

 pione

0.62

JR

0.60

 subur

0.60

Activations Density 0.038%

addresses or locations in California

U.S. state abbreviations and their occurrences in text

No Comments

No Known Activations