INDEX

Explanations

terms related to performance and measurements

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

"performance" and subsequent actions

np_acts-logits-general · gemini-2.0-flash

performance and its context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 فريبيس

-0.95

 defaultstate

-0.76

ness

-0.67

 transférez

-0.65

ConstraintMaker

-0.63

RenderAtEndOf

-0.63

 كمان

-0.61

 profonde

-0.61

 للمعارف

-0.60

unzel

-0.59

POSITIVE LOGITS

 arts

0.67

art

0.61

Performances

0.56

 enhancing

0.52

 metrics

0.52

 onPostExecute

0.51

 indicators

0.51

 ARTS

0.50

 Arts

0.49

@{

0.49

Activations Density 0.137%

terms related to performance and measurements

"performance" and subsequent actions

performance and its context

No Comments

No Known Activations