INDEX

Explanations

text related to licenses and legal permissions

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

before "license" or "families"

np_acts-logits-general · gemini-2.0-flash

license terms and conditions

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 tartalomajánló

-0.59

әрмәләр

-0.55

-0.53

 <<<<<<<<<<<<<<

-0.52

 дописавши

-0.51

-0.46

 internetowa

-0.42

MENAFN

-0.42

Cyfeiriadau

-0.42

InjectAttribute

-0.42

POSITIVE LOGITS

LookAnd

0.72

 HttpNotFound

0.70

NamedQueries

0.67

IContainer

0.65

AntiForgeryToken

0.61

 <>",

0.60

enderror

0.59

netinet

0.57

WillAppear

0.57

bootstrapcdn

0.57

Activations Density 0.141%

text related to licenses and legal permissions

before "license" or "families"

license terms and conditions

No Comments

No Known Activations