INDEX

Explanations

proper nouns, especially names of people and organizations

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

حياته

-0.61

complexContent

-0.60

őzés

-0.54

Дереккөздер

-0.53

Demografía

-0.53

 intptr

-0.53

<()>

-0.52

تفصیلات

-0.51

FXMLLoader

-0.50

 odkazy

-0.49

POSITIVE LOGITS

 disambiguazione

0.82

SupportActionBar

0.66

contentLoaded

0.63

NOPQRST

0.62

 réc

0.61

Pfe

0.56

IUrlHelper

0.55

 Waray

0.55

Personensuche

0.55

astéro

0.54

Activations Density 0.165%

proper nouns, especially names of people and organizations

No Comments

No Known Activations