INDEX

Explanations

occurrences of the word "feature" and related terms in discussions of technology or methods

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

"feature" followed by related terms

np_acts-logits-general · gemini-2.0-flash

feature followed by noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Искәрмәләр

-0.69

 Abbé

-0.69

PVA

-0.67

idp

-0.63

 ComVisible

-0.60

AccessFile

-0.60

 dõi

-0.59

IonicModule

-0.59

uegos

-0.59

missions

-0.58

POSITIVE LOGITS

 prominently

1.00

 features

0.86

features

0.80

 Features

0.76

Features

0.74

 feature

0.72

 FEATURE

0.69

 FEATURES

0.67

 Feature

0.65

フォン

0.63

Activations Density 0.136%

occurrences of the word "feature" and related terms in discussions of technology or methods

"feature" followed by related terms

feature followed by noun

No Comments

No Known Activations