INDEX

Explanations

structures and formatting related to mathematical arrays and matrix representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ⓧ

-0.86

 surla

-0.65

évaluateur

-0.63

chay

-0.61

bitan

-0.60

 siap

-0.60

quels

-0.59

tanooga

-0.59

};*/

-0.59

Datuak

-0.59

POSITIVE LOGITS

 prisonniers

0.68

 DbType

0.64

 falleció

0.60

 Tại

0.59

 belas

0.59

ecore

0.58

 noires

0.57

providedIn

0.57

 caduta

0.57

why

0.56

Activations Density 0.057%

structures and formatting related to mathematical arrays and matrix representations

No Comments

No Known Activations