INDEX

Explanations

texts that describe or present evidence, results, or specific details in various studies or analyses

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

Followed by "of," "about," "using," or "showed."

np_acts-logits-general · gemini-2.0-flash

presenting many details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-0.63

enderror

-0.55

 Paglinawan

-0.53

лтемелер

-0.52

ViewImports

-0.52

PreExecute

-0.52

brenner

-0.52

 deltaTime

-0.52

 defaultstate

-0.51

elemField

-0.49

POSITIVE LOGITS

 galore

0.70

 ranging

0.54

 زیادی

0.50

 such

0.46

 like

0.45

apl

0.42

 بیشتری

0.41

 beyond

0.40

 רבים

0.40

 takie

0.40

Activations Density 0.550%

texts that describe or present evidence, results, or specific details in various studies or analyses

Followed by "of," "about," "using," or "showed."

presenting many details

No Comments

No Known Activations