INDEX

Explanations

computer programming and markup language specifications

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

 Geſch

-0.63

 >=",

-0.59

geslacht

-0.57

 Administrativna

-0.57

 setUsername

-0.56

 Geſ

-0.54

ByExample

-0.54

 現貨

-0.53

 ſind

-0.53

 müſſen

-0.53

POSITIVE LOGITS

edge

0.47

MigrationBuilder

0.46

 edge

0.40

AutoField

0.39

VersionUID

0.39

setViewportView

0.39

dropIfExists

0.37

Edge

0.37

enterOuterAlt

0.36

 Edge

0.36

Activations Density 0.000%

computer programming and markup language specifications

<start_of_turn> user

No Comments

No Known Activations