INDEX

Explanations

references to programming concepts and structures

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

 שוליים

-0.89

fromnode

-0.86

OGND

-0.79

Diweddarwch

-0.74

DeleteBehavior

-0.70

ttemberg

-0.69

帖最后由

-0.69

enumi

-0.68

Hozzáférés

-0.67

IndentedString

-0.67

POSITIVE LOGITS

 prawa

0.45

 foundation

0.43

OOTDTY

0.42

nid

0.41

 pasas

0.39

 newList

0.39

دانشنامهٔ

0.39

description

0.38

show

0.38

 satisfaction

0.38

Activations Density 1.405%

references to programming concepts and structures

No Comments

No Known Activations