INDEX

Explanations

numerical representations and identifiers

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

code snippets and citations

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

出版年

-0.51

Pranala

-0.44

KURZBESCHREIBUNG

-0.42

rungsseite

-0.40

Normdaten

-0.36

addGap

-0.35

 engran

-0.34

 NSCoder

-0.34

 pozor

-0.34

Katso

-0.34

POSITIVE LOGITS

IUrlHelper

0.54

UAS

0.51

jsxFileName

0.51

 يتيمه

0.48

setForeground

0.47

cambrian

0.47

estrian

0.47

Atoi

0.46

IAA

0.46

FIC

0.46

Activations Density 0.017%

numerical representations and identifiers

code snippets and citations

No Comments

No Known Activations