INDEX

Explanations

references to organization and categorization of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 onCreateView

-0.81

-0.61

ticity

-0.58

PasswordEncoder

-0.57

easeOut

-0.55

drawImage

-0.55

beet

-0.54

 createSlice

-0.52

IEVE

-0.51

vieja

-0.51

POSITIVE LOGITS

 each

1.72

 every

1.64

every

1.44

 chaque

1.42

each

1.41

Each

1.40

 EACH

1.32

 bawat

1.31

 ogni

1.30

Every

1.30

Activations Density 0.403%

references to organization and categorization of information

No Comments

No Known Activations