INDEX

Explanations

elements related to code structure and definitions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

`ng`, `il`, `log` identifiers

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

Negative Logits

AddTagHelper

-0.70

WriteTagHelper

-0.68

ьаж

-0.68

 Comprometido

-0.68

 BoxFit

-0.65

 pinulongan

-0.63

OGND

-0.63

 surla

-0.63

 Italijani

-0.63

writeField

-0.61

POSITIVE LOGITS

 data

0.52

log

0.48

 existing

0.47

 flat

0.47

Ke

0.45

beforeSend

0.45

 means

0.43

 band

0.43

 trial

0.43

 criteria

0.43

Activations Density 0.008%

elements related to code structure and definitions

`ng`, `il`, `log` identifiers

No Known Activations