INDEX

Explanations

references to well-known designs or types of objects

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

Variations and types of something

np_acts-logits-general · gemini-2.0-flash

types and forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 increí

-0.45

 dépenses

-0.45

 zwiſchen

-0.43

 paſſ

-0.43

 zuſammen

-0.42

 desmotivaciones

-0.42

 vettoriale

-0.42

 iſt

-0.42

 ValidationError

-0.42

 relevante

-0.41

POSITIVE LOGITS

 variations

0.66

 variants

0.65

variations

0.62

 varieties

0.62

 styles

0.61

popular

0.58

 types

0.56

 Varianten

0.54

variants

0.54

 ujednoznacz

0.54

Activations Density 0.402%

references to well-known designs or types of objects

Variations and types of something

types and forms

No Comments

No Known Activations

references to well-known designs or types of objects

Variations and types of something

types and forms

No Comments

No Known Activations