INDEX

Explanations

mathematical expressions or code snippets

oai_token-act-pair · gemini-2.0-flash

arithmetic, math

np_max-act · gemini-2.0-flash

arithmetic

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

<bos>

-0.59

 оригіналу

-0.55

 ECTS

-0.47

queryInterface

-0.46

styleType

-0.44

tangentMode

-0.42

cydow

-0.42

cork

-0.42

closedir

-0.41

basicConfig

-0.40

POSITIVE LOGITS

исленность

0.72

EndContext

0.60

Kontrola

0.58

ParallelGroup

0.55

 consultato

0.54

ionales

0.53

COUVER

0.51

ReusableCell

0.51

 religieuse

0.51

loride

0.51

Activations Density 3.144%

mathematical expressions or code snippets

arithmetic, math

arithmetic

No Comments

No Known Activations