INDEX

Explanations

words and short sentences that ask questions

oai_token-act-pair · gemini-2.0-flash

specific coding or programming language terms

np_token-act-pair-logits · gpt-4o-mini

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 avancé

-0.52

bewerken

-0.49

adaptiveStyles

-0.48

BuilderFactory

-0.46

HÀ

-0.45

кви

-0.45

dotenv

-0.45

 fallu

-0.45

 livré

-0.44

 mémor

-0.44

POSITIVE LOGITS

SequentialGroup

0.62

Distribución

0.60

 cherchés

0.57

">—

0.55

intendent

0.55

!*\

0.55

itettura

0.52

trous

0.52

UserScript

0.52

columnName

0.51

Activations Density 9.226%

words and short sentences that ask questions

specific coding or programming language terms

No Comments

No Known Activations