INDEX

Explanations

statistical analysis terms and concepts

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

regression analysis models

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

MeasureSpec

-0.73

Efq

-0.65

íše

-0.63

isseurs

-0.59

 ſta

-0.59

 bershka

-0.59

 themſelves

-0.57

 Grit

-0.56

 himſelf

-0.56

vocable

-0.56

POSITIVE LOGITS

cab

0.54

Cab

0.50

Cab

0.50

 andata

0.48

 propOrder

0.45

setVerticalGroup

0.45

 Komis

0.43

matchCondition

0.43

ntax

0.42

навли

0.42

Activations Density 0.549%

statistical analysis terms and concepts

regression analysis models

No Comments

No Known Activations