INDEX

Explanations

nouns and actions associated with processes or events

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

temporal sequence before

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

KURZBESCHREIBUNG

-0.62

keyColumn

-0.56

GraphicsUnit

-0.51

 صوتيه

-0.50

 Administrativna

-0.49

 AssertionError

-0.49

ngrx

-0.48

Lähteet

-0.47

 snippetHide

-0.47

parsedMessage

-0.47

POSITIVE LOGITS

 Prior

0.45

 also

0.45

 prior

0.44

also

0.44

 PRIOR

0.43

 preceded

0.42

prior

0.41

 Also

0.41

Prior

0.40

 beforehand

0.38

Activations Density 0.000%

nouns and actions associated with processes or events

temporal sequence before

No Comments

No Known Activations