INDEX

Explanations

documents that contain detailed descriptions of trails or paths

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

Mathematical notation within text

np_acts-logits-general · gemini-2.0-flash

\mkern-2mu

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

InitVars

-0.75

 Ceramby

-0.60

Parcelize

-0.56

veer

-0.55

цездатний

-0.52

JpaRepository

-0.51

 EClass

-0.51

enderror

-0.49

onar

-0.49

fieldLabel

-0.48

POSITIVE LOGITS

UTF

1.02

UTF

0.86

出版年

0.79

IMPORTED

0.70

httphttps

0.69

uxxxx

0.66

IsContent

0.64

findpost

0.64

存于互联网档案馆

0.61

AutoScaleMode

0.60

Activations Density 0.016%

documents that contain detailed descriptions of trails or paths

Mathematical notation within text

\mkern-2mu

No Comments

No Known Activations