INDEX

Explanations

names or terms related to people or places

oai_token-act-pair · gpt-3.5-turbo

specific names and terms related to people or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ijing

-0.49

 recognise

-0.47

ÄŁ

-0.47

Äģ

-0.46

Ã¨

-0.46

fecture

-0.46

ynes

-0.44

ÂŃ

-0.43

zn

-0.43

UK

-0.43

POSITIVE LOGITS

 confir

0.45

 Trayvon

0.42

 Cutter

0.41

nesday

0.40

 Greenberg

0.40

 Vaugh

0.38

 Kessler

0.37

 Cooke

0.37

another

0.37

 pandemonium

0.37

Activations Density 2.374%

names or terms related to people or places

specific names and terms related to people or organizations

No Comments

No Known Activations