INDEX

Explanations

nodes and their properties in a programming context

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

ECONDS

-0.42

EndGlobalSection

-0.41

IntoConstraints

-0.40

 slippery

-0.40

 paralle

-0.39

ص

-0.39

 psycopg

-0.39

居

-0.39

çoit

-0.39

riffe

-0.39

POSITIVE LOGITS

 initComponents

0.80

 StatelessWidget

0.72

ⓧ

0.71

日閲覧

0.70

存于互联网档案馆

0.69

неопр

0.66

Hentet

0.65

 يتيمه

0.64

 IndexPath

0.64

thâu

0.64

Activations Density 0.303%

nodes and their properties in a programming context

No Comments

No Known Activations