INDEX

Explanations

references to specific individuals and their actions in legal or financial contexts

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

actions related to names

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

modelBuilder

-0.41

 sota

-0.32

ObjectContext

-0.32

 continuidad

-0.32

 Rücks

-0.31

 formales

-0.30

 rusak

-0.30

 tró

-0.30

 usan

-0.30

AllowAnonymous

-0.30

POSITIVE LOGITS

 MainAxisSize

0.54

 JpaRepository

0.52

 transfieras

0.51

expandindo

0.50

berdayakan

0.50

 volunte

0.48

Datuak

0.48

躇

0.48

olybden

0.48

rungsseite

0.48

Activations Density 0.064%

references to specific individuals and their actions in legal or financial contexts

actions related to names

No Comments

No Known Activations