INDEX

Explanations

references to databases, institutions, and scientific species or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

########.

-0.71

دانشنامهٔ

-0.65

Życiorys

-0.65

Ecotoxicity

-0.65

istoitu

-0.63

 cdti

-0.62

 disambiguazione

-0.62

 onCreateView

-0.62

EDEFAULT

-0.61

InitVars

-0.61

POSITIVE LOGITS

 typelib

0.51

 include

0.49

msgTypes

0.45

 eligible

0.43

addPreferredGap

0.43

texttt

0.43

 listed

0.41

 viết

0.41

é

0.41

 exclude

0.41

Activations Density 0.215%

references to databases, institutions, and scientific species or conditions

No Comments

No Known Activations