INDEX

Explanations

variations and modifications of terms or concepts

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

changes or versions

np_acts-logits-general · gemini-2.0-flash

version or modified states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

expandindo

-0.60

 propOrder

-0.51

Embeddable

-0.48

liğini

-0.47

 absolutamente

-0.46

CGContext

-0.46

estones

-0.45

NamedQuery

-0.45

 dataSnapshot

-0.45

jkl

-0.45

POSITIVE LOGITS

 version

1.80

 versions

1.57

 versión

1.31

 VERSION

1.26

版的

1.24

版

1.23

version

1.19

 Version

1.19

 versione

1.12

 versiones

1.11

Activations Density 0.468%

variations and modifications of terms or concepts

changes or versions

version or modified states

No Comments

No Known Activations