INDEX

Explanations

numerically indexed software version information

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

start of user turn

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

onedDateTime

-0.51

ukone

-0.50

 GenerationType

-0.48

AntiForgeryToken

-0.47

 cheveux

-0.47

dagogik

-0.46

 sukienka

-0.44

 torebka

-0.43

orghini

-0.42

 bluzka

-0.42

POSITIVE LOGITS

 defaultstate

0.56

 चीज़ों

0.50

 jadx

0.50

Cyfeiriadau

0.47

 comuniques

0.45

المكان

0.45

Personensuche

0.45

 Roskov

0.44

tagHelperRunner

0.43

 Numerade

0.43

Activations Density 0.000%

numerically indexed software version information

start of user turn

No Comments

No Known Activations