INDEX

Explanations

words relating to decreases or reductions

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

dropped by or in

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

RTDA

-0.59

 autorytatywna

-0.59

 OnInit

-0.59

دانشنامهٔ

-0.56

 AssemblyTitle

-0.55

 valueForKey

-0.54

theon

-0.53

 Италијани

-0.53

entityManager

-0.52

 DataTypes

-0.52

POSITIVE LOGITS

 drop

1.88

 dropped

1.84

drop

1.75

 Drop

1.71

 dropping

1.65

Drop

1.63

 DROP

1.59

dropped

1.55

 drops

1.55

Dropped

1.48

Activations Density 0.010%

words relating to decreases or reductions

dropped by or in

No Comments

No Known Activations