INDEX

Explanations

proper nouns and names related to individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Nö

-0.48

glGen

-0.47

Rä

-0.46

pha

-0.44

googleapis

-0.43

strengthen

-0.42

ɹ

-0.42

coon

-0.41

 зале

-0.40

FFFF

-0.40

POSITIVE LOGITS

 nahilalakip

0.93

 >=",

0.89

 InputDecoration

0.80

 CreateTagHelper

0.77

 незавершена

0.77

ViewFeatures

0.76

OGND

0.75

 Biôgrafia

0.72

 Administrativna

0.69

 Spisak

0.69

Activations Density 0.268%

proper nouns and names related to individuals and entities

No Comments

No Known Activations