INDEX

Explanations

mentions of battles and associated events.

oai_token-act-pair · gemini-2.0-flash

Describing conflict or battles

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 MaterialApp

-0.62

COUVER

-0.53

IVEREF

-0.52

sidemargin

-0.49

VersionUID

-0.46

 izquier

-0.45

 cipolla

-0.44

 personaje

-0.43

 femminile

-0.43

 eriş

-0.43

POSITIVE LOGITS

Efq

0.66

 fight

0.66

IsContent

0.63

 Monfieur

0.61

adpleegd

0.60

 rematch

0.59

 quarrel

0.59

 estimés

0.59

thday

0.58

fight

0.57

Activations Density 2.304%

mentions of battles and associated events.

Describing conflict or battles

No Comments

No Known Activations