INDEX

Explanations

specific brand names or product identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.53

gebra

-0.51

 items

-0.51

SizeMode

-0.49

 solutions

-0.48

 areas

-0.47

 information

-0.46

 material

-0.45

 patterns

-0.45

POSITIVE LOGITS

 AssemblyCompany

0.82

__":

0.82

 JpaRepository

0.81

__':

0.79

HomeAsUpEnabled

0.77

RemoteException

0.75

—

0.73

IBOutlet

0.70

inerja

0.70

 saites

0.70

Activations Density 0.484%

specific brand names or product identifiers

No Comments

No Known Activations