INDEX

Explanations

references to programming and coding concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ⓧ

-0.77

-0.71

onOptions

-0.70

WireFormatLite

-0.70

ValueStyle

-0.69

Diwedd

-0.69

 Infórmanos

-0.69

 تضيفلها

-0.68

reportError

-0.68

}{*}{}

-0.67

POSITIVE LOGITS

{\

0.43

DrawerToggle

0.42

 незавершена

0.41

 impli

0.41



0.40

 eius

0.40

raborty

0.40

antaranya

0.40

 revés

0.38

 colspan

0.38

Activations Density 0.037%

references to programming and coding concepts

No Comments

No Known Activations