INDEX

Explanations

various types of items or features, often describing characteristics or attributes

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

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

 يتيمه

-1.09

UserScript

-0.81

Hentet

-0.78

tagHelperRunner

-0.77

Vidite

-0.75

 AssemblyCompany

-0.73

 oreille

-0.73

ItemBackground

-0.72

IntoConstraints

-0.71

terase

-0.69

POSITIVE LOGITS

 large

0.73

 assortment

0.72

 Vielzahl

0.67

 variety

0.67

mix

0.65

 selection

0.61

 multitude

0.60

 myriad

0.59

 plethora

0.59

 array

0.59

Activations Density 0.403%

various types of items or features, often describing characteristics or attributes

No Comments

No Known Activations