INDEX

Explanations

references to articles and information related to web content

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

URLs, often Wikipedia links

np_acts-logits-general · gemini-2.0-flash

URLs and Wikipedia links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.49

fortawesome

-0.49

 învă

-0.44

írito

-0.44

orc

-0.43

roso

-0.43

 întâ

-0.42

ifolium

-0.42

Bottle

-0.42

JEFF

-0.41

POSITIVE LOGITS

rungsseite

0.48

 typelib

0.41

 betweenstory

0.41

TestingModule

0.40

PreferredItem

0.40

">//

0.40

tagHelperRunner

0.38

httphttps

0.37

 Exactos

0.37

 Italijani

0.36

Activations Density 0.012%

references to articles and information related to web content

URLs, often Wikipedia links

URLs and Wikipedia links

No Comments

No Known Activations