INDEX

Explanations

technical terms and coding structures related to programming and algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

inė

-0.46

AntiForgeryToken

-0.44

うちに

-0.44

要在

-0.43

 dual

-0.41

절

-0.41

 esquecer

-0.41

Med

-0.40

ποίη

-0.40

dup

-0.40

POSITIVE LOGITS

 IBOutlet

0.88

StoryboardSegue

0.83

IBOutlet

0.75

 afterlife

0.75

twimg

0.74

posedge

0.73

stateProvider

0.71

MLLoader

0.68

routeProvider

0.67

ThroughAttribute

0.65

Activations Density 0.730%

technical terms and coding structures related to programming and algorithms

No Comments

No Known Activations