INDEX

Explanations

programming and coding-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 confirmation

-0.33

 diing

-0.30

bli

-0.29

 Brin

-0.29

 juice

-0.29

 temple

-0.29

 cold

-0.29

 comfortable

-0.28

ab

-0.28

 abbre

-0.27

POSITIVE LOGITS

AndEndTag

0.73

ကိုးကား

0.64

 surla

0.63

Vidite

0.59

__":

0.58

hyrchwyd

0.56

webElementXpaths

0.56

awtextra

0.53

 createSprite

0.53

Personendaten

0.52

Activations Density 0.329%

programming and coding-related terminology

No Comments

No Known Activations