INDEX

Explanations

keywords related to explicitness or clear articulation in a context

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

explicit details or statements

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

 للمعارف

-0.72

 getNumber

-0.64

ValueStyle

-0.59

NavController

-0.56

เดียว

-0.54

 baterías

-0.54

ServiceModel

-0.53

 ventas

-0.52

 rowCount

-0.52

 zdrowia

-0.52

POSITIVE LOGITS

 explicit

0.77

Explicit

0.73

explicit

0.72

 Explicit

0.72

 explicitly

0.61

 explí

0.57

__*/

0.57

implicit

0.55

 expression

0.53

PLICIT

0.52

Activations Density 0.011%

keywords related to explicitness or clear articulation in a context

explicit details or statements

No Comments

No Known Activations