INDEX

Explanations

expressions indicating disagreement or contention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

værende

-0.56

GraphicsUnit

-0.55

代替

-0.53

labelledby

-0.52

 Paglinawan

-0.52

Хьажоргаш

-0.51

tonode

-0.51

ftagPool

-0.50

verifyException

-0.50

 Emits

-0.49

POSITIVE LOGITS

tagext

0.58

 setOpen

0.56

DockStyle

0.54

malink

0.51

kháu

0.47

 ViewPager

0.47

astify

0.46

let

0.46

kfree

0.45

 SearchView

0.45

Activations Density 0.133%

expressions indicating disagreement or contention

No Comments

No Known Activations