INDEX

Explanations

the concept of displaying or indicating something, particularly in relation to progress or support

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

"Show" or related words

np_acts-logits-general · gemini-2.0-flash

showing up or demonstrating actions

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

StoryboardSegue

-0.64

yntaxException

-0.56

oa̍t

-0.52

 silence

-0.51

zünd

-0.51

 screams

-0.50

lihood

-0.50

 silencio

-0.49

audiovisuel

-0.48

 conseillé

-0.48

POSITIVE LOGITS

how

0.78

SpringBootTest

0.77

 signs

0.74

 signes

0.74

 Showing

0.72

 Shows

0.69

 SIGNS

0.68

Showing

0.64

 montrer

0.64

 clearly

0.63

Activations Density 0.203%

the concept of displaying or indicating something, particularly in relation to progress or support

"Show" or related words

showing up or demonstrating actions

No Comments

No Known Activations