INDEX

Explanations

HTML code snippets, and text related to discussion boards, possibly questions and answers.

oai_token-act-pair · gemini-2.0-flash

mixed content internet posts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 חיצוניים

-0.65

 يتيمه

-0.56

 nahilalakip

-0.55

providedIn

-0.54

 Theſe

-0.53

UnsafeEnabled

-0.50

 виправивши

-0.46

 autorytatywna

-0.43

 saites

-0.41

Diwedd

-0.40

POSITIVE LOGITS

batman

0.63

addGap

0.60

LMAO

0.58

moncler

0.57

imgur

0.57

ffindor

0.57

kpop

0.56

horabuena

0.56

woah

0.55

Ikr

0.54

Activations Density 36.572%

HTML code snippets, and text related to discussion boards, possibly questions and answers.

mixed content internet posts

No Comments

No Known Activations

HTML code snippets, and text related to discussion boards, possibly questions and answers.

mixed content internet posts

No Comments

No Known Activations