INDEX

Explanations

references to procedural or technical details in a scientific context

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

functional verbs and punctuation

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

httphttps

-0.88



-0.60

tonode

-0.59

 بيها

-0.53

richTextPanel

-0.51

はじめに

-0.46

帖最后由

-0.46

éez

-0.46

̈́

-0.45

crapers

-0.45

POSITIVE LOGITS

SuspendLayout

0.43

AutoField

0.39

RectangleBorder

0.37

 disambiguazione

0.36

Бахар

0.36

-------------</

0.35

disposing

0.35

띄

0.33

dafx

0.33

atimes

0.33

Activations Density 0.063%

references to procedural or technical details in a scientific context

functional verbs and punctuation

No Comments

No Known Activations