INDEX

Explanations

programming language keywords and definitions

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

macro definitions

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

transQ

-0.91

 ExecuteAsync

-0.66

RegressionTest

-0.65

 الحره

-0.62

__':

-0.61

 ErrIntOverflow

-0.57

 pinulongan

-0.56

 Paglinawan

-0.55

 queſto

-0.55

enumi

-0.55

POSITIVE LOGITS

IntoConstraints

0.47

 wyś

0.35

penup

0.34

 poroz

0.34

 lendemain

0.32

iteurs

0.31

 căr

0.31

 Kapol

0.30

 vanske

0.29

gjenge

0.29

Activations Density 0.068%

programming language keywords and definitions

macro definitions

No Comments

No Known Activations