INDEX

Explanations

questions and requests for information or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 تكبرها

-0.49

 createSlice

-0.49

 actifs

-0.49

 gloire

-0.47

 propriedade

-0.47

 vaisselle

-0.47

zmir

-0.44

 even

-0.44

 alá

-0.43

leş

-0.43

POSITIVE LOGITS

AnimationsModule

0.75

 InputDecoration

0.71

 AssemblyCulture

0.68

expandindo

0.68

 NSCoder

0.67

libft

0.64

!("{

0.61

<?

0.61

__":

0.61

DockStyle

0.59

Activations Density 0.412%

questions and requests for information or clarification

No Comments

No Known Activations