INDEX

Explanations

symbols, formatting characters, and special markers commonly used in programming or document structuring

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

academic citations and references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

Šaltiniai

-0.31

 veau

-0.31

 Choice

-0.31

🔕

-0.30

Choice

-0.30

 Donc

-0.30

ThemeOverlay

-0.29

 Numerade

-0.29

بوابة

-0.28

 huel

-0.28

POSITIVE LOGITS

arangay

0.60

 EconPapers

0.58

unicip

0.57

 CreateTagHelper

0.54

 Normdatei

0.54

ikusbot

0.54

iſter

0.52

bootstrapcdn

0.51

cilis

0.50

BibitemShut

0.50

Activations Density 0.144%

symbols, formatting characters, and special markers commonly used in programming or document structuring

academic citations and references

No Comments

No Known Activations