INDEX

Explanations

numerical values or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

-1.02

findpost

-0.93

 Accesat

-0.90

 Lucía

-0.78

SBATCH

-0.75

 ویکی‌پدیا

-0.73

 تضيفلها

-0.71

tvguidetime

-0.71

 Perſ

-0.71

\{\\

-0.70

POSITIVE LOGITS

ViewFeatures

0.61

alyptus

0.60

Emm

0.59

RegressionTest

0.58

 Schein

0.56

taux

0.55

ַע

0.54

chet

0.52

 Eichen

0.52

راعة

0.51

Activations Density 0.354%

numerical values or measurements

No Comments

No Known Activations