INDEX

Explanations

references to awards and recognitions

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

awards and "times"

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

AccessorTable

-0.57

Biografía

-0.51

Життєпис

-0.50

 '\\;'

-0.49

complexContent

-0.49

feer

-0.49

InputTagHelper

-0.48

الحياه

-0.47

contentLoaded

-0.47

yyr

-0.47

POSITIVE LOGITS

 award

0.61

 awarded

0.52

 awards

0.52

 récomp

0.50

 medal

0.49

 AWARD

0.49

 recognition

0.48

🏆

0.47

 récompense

0.47

 prize

0.47

Activations Density 0.039%

references to awards and recognitions

awards and "times"

No Comments

No Known Activations