INDEX

Explanations

negations or expressions of doubt

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

negations using don’t, doesn’t, isn’t

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

 وتسجيلات

-0.51

AnchorTagHelper

-0.50

WebServlet

-0.48

 pinulongan

-0.46

новништво

-0.45

DockStyle

-0.44

PreExecute

-0.43

EDEFAULT

-0.41

bumptech

-0.41

 usah

-0.41

POSITIVE LOGITS

 referrerpolicy

0.61

发表于

0.59

 okuyayım

0.52

 Administrativna

0.46

 Meksiku

0.45

 kaarangay

0.44

tinyos

0.43

Aholisi

0.43

$_['

0.42

 Савезне

0.42

Activations Density 0.012%

negations or expressions of doubt

negations using don’t, doesn’t, isn’t

No Comments

No Known Activations