INDEX

Explanations

formatting elements and syntax structure in code or markup languages

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

programming code contexts

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 змо

-0.32

bin

-0.31

ച്

-0.31

 WATSON

-0.31

úc

-0.31

 Watson

-0.30

ito

-0.30

 δε

-0.29

ser

-0.29

 उत्

-0.29

POSITIVE LOGITS

IUrlHelper

0.94

 EconPapers

0.90

rungsseite

0.81

__*/

0.76

 Taktlose

0.73

 kasarigan

0.72

httphttps

0.70

 Италијани

0.70

 ProtoMessage

0.69

 cherchés

0.69

Activations Density 0.001%

formatting elements and syntax structure in code or markup languages

programming code contexts

No Comments

No Known Activations