INDEX

Explanations

instances of decision-making and conditional logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 conmigo

-0.76

 comigo

-0.74

 meille

-0.62

してくれます

-0.61

 niya

-0.60

 AssemblyCulture

-0.55

seamnă

-0.55

новниш

-0.54

sobí

-0.53

 знают

-0.53

POSITIVE LOGITS

 ourselves

0.64

am

0.58

we

0.55

دانشنامهٔ

0.53

եմ

0.53

som

0.53

出版年

0.52

IAM

0.51

Stam

0.50

Activations Density 0.065%

instances of decision-making and conditional logic

No Comments

No Known Activations