INDEX

Explanations

references to visual media and URLs

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

urls and links

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

KommentareTeilen

-0.60

AddTagHelper

-0.59

 autorytatywna

-0.59

DockStyle

-0.58

 surla

-0.56

argout

-0.56

GEBURTSDATUM

-0.55

Distribuzione

-0.54

énario

-0.51

PositiveButton

-0.51

POSITIVE LOGITS

)$/,

0.35

 SafeMath

0.35

QRST

0.35

detail

0.34

нциклопе

0.34

 pics

0.33

 注意

0.33

HideFlags

0.32

留意

0.32

 pictures

0.32

Activations Density 0.003%

references to visual media and URLs

urls and links

No Comments

No Known Activations