INDEX

Explanations

programmatic structures such as functions or methods, indicated by parentheses and curly braces

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.60

 prospect

-0.57

mybatisplus

-0.56

IContainer

-0.56

indere

-0.55

 utafitiHapana

-0.53

 مرئيه

-0.52

 intptr

-0.51

TabView

-0.50

stdbool

-0.50

POSITIVE LOGITS

addCriterion

0.71

AlterField

0.62

__':

0.60

dafx

0.58

InvalidProtocol

0.55

 venons

0.52

 uska

0.52

 ComVisible

0.52

 Wikispecies

0.52

RTLD

0.52

Activations Density 0.011%

programmatic structures such as functions or methods, indicated by parentheses and curly braces

No Comments

No Known Activations