INDEX

Explanations

legal terminology related to licensing agreements

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

terms of the

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

 ✭✭

-0.54

 cresc

-0.44

 plong

-0.43

 pareil

-0.43

 createContext

-0.41

 greateſt

-0.41

 ſte

-0.40

 ſch

-0.40

 dispar

-0.39

 afric

-0.39

POSITIVE LOGITS

tagHelperRunner

0.62

 terms

0.62

AnchorStyles

0.55

 resourceCulture

0.55

ViewFeatures

0.55

terms

0.54

 conditions

0.51

Terms

0.51

ValueStyle

0.50

 defaultstate

0.49

Activations Density 0.007%

legal terminology related to licensing agreements

terms of the

No Comments

No Known Activations