INDEX

Explanations

references to programming constructs or libraries in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 виправивши

-0.57

IndentedString

-0.45

 autorytatywna

-0.44

 Superan

-0.44

afficheront

-0.42

Embeddable

-0.42

SourceChecksum

-0.41

corazón

-0.36

 سكانية

-0.35

 Grèce

-0.35

POSITIVE LOGITS

 defaultstate

0.58

 Schna

0.47

usercontent

0.45

cycline

0.45

aust

0.44

 Cast

0.42

SerializedName

0.42

Lau

0.42

 flapping

0.42

gotoxy

0.40

Activations Density 0.041%

references to programming constructs or libraries in code

No Comments

No Known Activations