INDEX

Explanations

special characters and formatting elements typically found in academic papers or documents

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

section markers or codes

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

 TextInputType

-0.53

 AssemblyCompany

-0.50

userdetails

-0.48

:✨

-0.47



-0.43

 igjen

-0.43

 bezeichneter

-0.43

BeginContext

-0.43

#+#

-0.43

достатки

-0.41

POSITIVE LOGITS

expandindo

0.54

setVerticalGroup

0.48

PreExecute

0.48

awtextra

0.46

ViewFeatures

0.46

MessageState

0.44

arXiv

0.44

\{\\

0.43

 الحره

0.43

 EconPapers

0.42

Activations Density 0.013%

special characters and formatting elements typically found in academic papers or documents

section markers or codes

No Comments

No Known Activations