INDEX

Explanations

references to tools and devices used for specific tasks or applications

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

purpose of tools or actions

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

 кӀош

-0.36

 Schilling

-0.36

DispatchQueue

-0.35

konzert

-0.34

 Pacheco

-0.34

 radical

-0.34

')[

-0.33

 חוש

-0.33

сован

-0.32

 Sonnen

-0.32

POSITIVE LOGITS

+#+#

0.87

httphttps

0.68

IsContent

0.65

:✨

0.62

Personendaten

0.60

ViewFeatures

0.59

0.56

#+#

0.56

 Perſ

0.55

 resourceCulture

0.54

Activations Density 0.017%

references to tools and devices used for specific tasks or applications

purpose of tools or actions

No Comments

No Known Activations