INDEX

Explanations

references to leadership and decision-making roles within various contexts

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

political positions and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.59

Personensuche

-0.53

 tartalomajánló

-0.49

 فريبيس

-0.48

 AssemblyTitle

-0.48

 AssemblyVersion

-0.46

FontStyle

-0.43

UserScript

-0.43

 StringTokenizer

-0.41

styleType

-0.40

POSITIVE LOGITS

tonode

0.51

 nawr

0.43

Alongside

0.42

 alongside

0.42

исленность

0.42

 Alongside

0.41

>*/

0.40

 चीज़ों

0.40

 andere

0.40

 junto

0.38

Activations Density 0.129%

references to leadership and decision-making roles within various contexts

political positions and outcomes

No Comments

No Known Activations