INDEX

Explanations

structured elements within technical or programming documentation

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

clinical sign versus disease

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

arbeid

-0.48

colta

-0.45

 Vertigo

-0.43

chesse

-0.41

masse

-0.41

 Matisse

-0.40

izel

-0.40

 materialize

-0.40

 shorten

-0.40

 consolidate

-0.40

POSITIVE LOGITS

Personendaten

0.59

 للاسماء

0.56

出版年

0.55

 onPostExecute

0.52

Tikang

0.52

StructEnd

0.52

 tartalomajánló

0.52

awtextra

0.52

FunctionFlags

0.52

setVerticalGroup

0.50

Activations Density 0.002%

structured elements within technical or programming documentation

clinical sign versus disease

No Comments

No Known Activations