INDEX

Explanations

references to deities or divine concepts

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.21

 ***!

-0.97

Autoritní

-0.91

RepeatedField

-0.89

rungsseite

-0.87

homonymie

-0.87

-------------</

-0.84

execSQL

-0.84

LookAnd

-0.83

 NSCoder

-0.83

POSITIVE LOGITS

 philanth

2.40

 stockholm

2.38

 milf

2.37

 affor

2.37

 snoopy

2.35

 Intere

2.34

aen

2.31

fta

2.28

 strick

2.26

 hentai

2.25

Activations Density 0.539%

references to deities or divine concepts

No Comments

No Known Activations