INDEX

Explanations

syntax related to programming, particularly variable declarations and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

出版年

-0.63

AccessorTable

-0.61

rature

-0.57

 partagé

-0.55

 cytochrome

-0.55

 GeoNames

-0.55

 Convex

-0.55

 collectivités

-0.54

cury

-0.54

 chré

-0.53

POSITIVE LOGITS

BeginContext

0.75

 vVar

0.63

 fVar

0.62

 iVar

0.62

 uLocal

0.59

 dilihat

0.54

 iParam

0.51

iVar

0.51

 noDo

0.51

esehen

0.49

Activations Density 0.114%

syntax related to programming, particularly variable declarations and function definitions

No Comments

No Known Activations