INDEX

Explanations

references to warranties and product details

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

<start_of_turn>user

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

versicherung

-0.29

 humo

-0.28

 diamants

-0.28

 Ärzte

-0.28

erialize

-0.28

 Brücke

-0.27

 Marine

-0.26

 helados

-0.26

 atmosf

-0.26

 jugement

-0.26

POSITIVE LOGITS

 surla

0.74

 propOrder

0.66

autorest

0.65

RegressionTest

0.63

Jeografia

0.61

 disambiguazione

0.60

ंदीखरीदारी

0.60

Personendaten

0.60

 '\\;'

0.60

 transfieras

0.58

Activations Density 0.014%

references to warranties and product details

<start_of_turn>user

No Comments

No Known Activations