INDEX

Explanations

specific programming-related syntax and structure, particularly dealing with sizes and dimensions

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

RegistryLite

-0.61

出版年

-0.56

RTCK

-0.52

:✨

-0.51

setLevel

-0.50

 martie

-0.50

ItemBackground

-0.50

Jereo

-0.48

 EconPapers

-0.48

 erfol

-0.46

POSITIVE LOGITS

 onCreateView

0.71

AnchorTagHelper

0.60

HTH

0.58

󠁿

0.58

sizeCache

0.56

jsonwebtoken

0.56

 timedelta

0.56

 myself

0.55

存于互联网档案馆

0.55

InBytes

0.53

Activations Density 0.068%

specific programming-related syntax and structure, particularly dealing with sizes and dimensions

No Comments

No Known Activations