INDEX

Explanations

references to products or items being introduced or described in detail

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

Followed by a capitalized word

np_acts-logits-general · gemini-2.0-flash

product names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

uxxxx

-0.69

JpaRepository

-0.57

+#+#

-0.56

crollView

-0.54

ISupport

-0.51

Související

-0.51

DockStyle

-0.49

stdc

-0.48

DBNull

-0.47

 Imperium

-0.46

POSITIVE LOGITS

 mijne

0.62

こいつ

0.61

 greateſt

0.61

 voici

0.61

 acestui

0.60

 gewiß

0.60

 piú

0.57

this

0.56

 recommandons

0.55

 RemoteException

0.54

Activations Density 0.364%

references to products or items being introduced or described in detail

Followed by a capitalized word

product names

No Comments

No Known Activations