INDEX

Explanations

indicators of numerical data and statistical analysis

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

comparing estimates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

enderror

-0.56

:✨

-0.55

)\}

-0.52

\}\\

-0.52

Rhestr

-0.49

 ComVisible

-0.49

fromnode

-0.48

 SqlDbType

-0.48

؜

-0.46

 snippetHide

-0.45

POSITIVE LOGITS

 accurate

0.46

 accuracy

0.45

 exact

0.45

 estimate

0.42

 estimates

0.41

 ESTIM

0.41

Accurate

0.41

AndEndTag

0.41

 estima

0.40

 สู

0.39

Activations Density 0.174%

indicators of numerical data and statistical analysis

comparing estimates

No Comments

No Known Activations