INDEX

Explanations

mathematical symbols and variables associated with equations and functions

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

modified, revised, corrected

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ब्रेकडाउन

-0.72

IsMutable

-0.65

aarrggbb

-0.57

tagext

-0.57

SharedDtor

-0.57

 вікі

-0.57

oneofs

-0.53

 Biôgrafia

-0.53

évaluateur

-0.53

 VizieR

-0.52

POSITIVE LOGITS

 modified

0.44

 revised

0.44

 distorted

0.43

 amended

0.43

 replaced

0.40

imp

0.40

 updated

0.40

 /\.(

0.38

 revisited

0.38

 corrected

0.38

Activations Density 0.144%

mathematical symbols and variables associated with equations and functions

modified, revised, corrected

No Comments

No Known Activations