INDEX

Explanations

phrases related to legal proceedings and negotiations

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

voluntary recall

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

EndContext

-0.50

msgTypes

-0.47

原始内容存档于

-0.47

canestro

-0.45

makeConstraints

-0.45

 Biôgrafia

-0.44

 المعيارى

-0.44

Absolutely

-0.43

IntoConstraints

-0.43

umet

-0.42

POSITIVE LOGITS

 voluntary

0.52

 friv

0.50

 voluntarily

0.47

 freiw

0.44

 volunt

0.42

 Voluntary

0.39

HtmlAttribute

0.38

localctx

0.37

oluntary

0.36

weichen

0.35

Activations Density 0.076%

phrases related to legal proceedings and negotiations

voluntary recall

No Comments

No Known Activations