INDEX

Explanations

instances of the verb "be" indicating existence or state

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

future states or actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 שוליים

-0.42

 pungkasnya

-0.40

cartão

-0.37

Šaltiniai

-0.37

 minOccurs

-0.35

 dallo

-0.34

 때문

-0.33

 autorytatywna

-0.33

ⁱ

-0.33

但我

-0.33

POSITIVE LOGITS

 Jefus

0.67

 Monfieur

0.65

 Chriftian

0.63

 poffe

0.61

 raiſ

0.60

 Diſ

0.60

 ſever

0.60

 Shakspeare

0.60

 esternos

0.60

Eſ

0.59

Activations Density 0.004%

instances of the verb "be" indicating existence or state

future states or actions

No Comments

No Known Activations