INDEX

Explanations

programming-related terminology and syntax

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

create(...), import, frac(..., {...})

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

MigrationBuilder

-0.63

 surla

-0.45

ceğim

-0.41

Scénario

-0.39

cupertino

-0.38

 JpaRepository

-0.36

IsPostBack

-0.36

iibo

-0.35

DllImport

-0.35

mittlung

-0.34

POSITIVE LOGITS

InitVars

0.52

 craindre

0.49

ércoles

0.47

saga

0.46

 Kitchens

0.45

Personendaten

0.45

pośred

0.44

Diweddarwch

0.44

 gynhyrchwyd

0.44

 wijze

0.44

Activations Density 0.001%

programming-related terminology and syntax

create(...), import, frac(..., {...})

No Comments

No Known Activations