INDEX

Explanations

маркированные слова или символы в тексте

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

AsUp

-0.84

žná

-0.59

nsito

-0.59

erevan

-0.57

syp

-0.56

 demografica

-0.56

 suscep

-0.54

 Bourgoin

-0.53

NewUrlParser

-0.53

่านั้น

-0.53

POSITIVE LOGITS

Σε

0.69

 Inscrivez

0.68

the

0.67

wixt

0.66

 Stubbs

0.65

于

0.65

parseFrom

0.62

Με

0.62

 InputDecoration

0.61

Voor

0.60

Activations Density 0.259%

маркированные слова или символы в тексте

No Comments

No Known Activations