INDEX

Explanations

brand names or specific entities

oai_token-act-pair · gpt-3.5-turbo

specific product or brand names

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

•San

#5 activation: 5.77

No Comments

Negative Logits

âĢķ

-0.63

âĢ¢âĢ¢

-0.61

––

-0.61

*.

-0.61

 accompanied

-0.60

}.

-0.58

.*

-0.58

 respons

-0.57

 âĢ¦"

-0.57

 inst

-0.56

POSITIVE LOGITS

Coin

0.80

Eye

0.78

Berry

0.78

Wire

0.75

isoft

0.74

Bot

0.73

Wing

0.72

coin

0.72

Fest

0.71

Sync

0.71

Activations Density 0.546%

brand names or specific entities

specific product or brand names

No Comments

No Known Activations