INDEX

Explanations

structured data definitions and configurations in code

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

android xml attributes

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

 sorpresas

-0.44

BufferException

-0.43

 Forsch

-0.35

 pouvoit

-0.35

 revelado

-0.34

 besos

-0.34

 oportunidades

-0.34

Vegeu

-0.33

まま

-0.33

CppCodeGen

-0.33

POSITIVE LOGITS

IndentedString

0.79

 nahilalakip

0.69

 للاسماء

0.62

RTLR

0.62

">//

0.58

SBATCH

0.56

ConstraintMaker

0.56

andExpect

0.54

KommentareTeilen

0.53

 CreateTagHelper

0.52

Activations Density 0.014%

structured data definitions and configurations in code

android xml attributes

No Comments

No Known Activations