INDEX

Explanations

the term "model" within the context of legal or technical documentation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

legal proceedings and documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 propOrder

-0.75

tvguidetime

-0.59

énario

-0.58

 kaynağından

-0.57

OGND

-0.57

Viitteet

-0.56

EDEFAULT

-0.56

featureID

-0.55

 <<<<<<<<<<<<<<

-0.52

Dichloropropane

-0.52

POSITIVE LOGITS

IndentedString

0.39

abs

0.33

Дереккөздер

0.33

 PeEnEo

0.32

styleable

0.32

auth

0.31

wget

0.31

 betweenstory

0.31

吋

0.30

Activations Density 0.005%

the term "model" within the context of legal or technical documentation

legal proceedings and documents

No Known Activations