INDEX

Explanations

legal terminology and references to court decisions

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

affirm or denied

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

 Saba

-0.36

thenReturn

-0.36

 abar

-0.34

stateProvider

-0.34

 Boch

-0.34

 reels

-0.34

setList

-0.34

ziali

-0.33

Véxase

-0.33

isLoggedIn

-0.33

POSITIVE LOGITS

UrlResolution

0.61

unref

0.55

SharedCtor

0.51

featureID

0.51

 contextLoads

0.50

ьаж

0.50

andExpect

0.49

 ***!

0.49

 مرئيه

0.48

JspWriter

0.48

Activations Density 0.142%

legal terminology and references to court decisions

affirm or denied

No Comments

No Known Activations