INDEX

Explanations

questions and inquiries related to understanding and discovery

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Jeografia

-0.45

marvin

-0.44

Willow

-0.42

 over

-0.41

 mutat

-0.41

now

-0.40

try

-0.39

cr

-0.37

 under

-0.36

POSITIVE LOGITS

StoryboardSegue

0.92

+#+#

0.83

Vidite

0.82

fjspx

0.77

webElementXpaths

0.77

GEBURTSDATUM

0.76

EndGlobalSection

0.76

RectangleBorder

0.74

enterOuterAlt

0.74

цездатний

0.73

Activations Density 0.459%

questions and inquiries related to understanding and discovery

No Comments

No Known Activations