INDEX

Explanations

programming-related terms and queries involving coding logic and functions

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

 aveug

-0.78

VIAF

-0.73

 mijne

-0.72

 bouteilles

-0.66

 bőr

-0.66

 sécur

-0.66

 venons

-0.66

 sánchez

-0.64

 desple

-0.64

sya

-0.64

POSITIVE LOGITS

PositiveButton

0.80

 LoginComponent

0.79

parsedMessage

0.78

FailureListener

0.77

 LoginPage

0.77

homonymie

0.77

Και

0.74

 تانيه

0.73

StoryboardSegue

0.72

 Designers

0.72

Activations Density 0.121%

programming-related terms and queries involving coding logic and functions

No Comments

No Known Activations