INDEX

Explanations

indicators of code structure or programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

География

-0.65

—

-0.62

UniformLocation

-0.62

 esternos

-0.61

bootstrapcdn

-0.60

enumi

-0.58

withIdentifier

-0.58

mybatisplus

-0.57

%)$

-0.56

 समीक्षक

-0.55

POSITIVE LOGITS

 ✭✭

0.68

 Inscrivez

0.65

 Monfieur

0.59

 Cæsar

0.57

xygen

0.55

 Bucure

0.55

 drago

0.54

 Abonnez

0.54

roek

0.54

 Tommaso

0.53

Activations Density 0.314%

indicators of code structure or programming syntax

No Comments

No Known Activations