INDEX

Explanations

identifiers related to memory or data attributes in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 officiels

-0.68

 Vikipedi

-0.60

 BIBSYS

-0.58

 кӀ

-0.56

GEBURTSDATUM

-0.54

ByPrimaryKey

-0.53

tagext

-0.53

 Bonner

-0.53

slidesToShow

-0.53

RDONLY

-0.52

POSITIVE LOGITS

Hochspringen

0.64

nx

0.60

 Rollo

0.60

 cyclones

0.59

 تضيفلها

0.56

 cyclone

0.56

GIP

0.53

 monkeys

0.52

 tigers

0.52

ProductService

0.52

Activations Density 1.063%

identifiers related to memory or data attributes in programming contexts

No Comments

No Known Activations