INDEX

Explanations

numerical values associated with effects or changes caused by skills

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

iprot

-0.54

addContainerGap

-0.53

허

-0.49

Portail

-0.47

-0.44

mas

-0.42

skap

-0.42

utt

-0.41

 Forrest

-0.41

utta

-0.41

POSITIVE LOGITS

……"

0.78

DoubleQuotes

0.75

 gepubliceerd

0.73

PhysRevD

0.72

+:+

0.72

 itſelf

0.71

WebVitals

0.71

 InputDecoration

0.70

."));

0.70

 pleaſure

0.68

Activations Density 0.114%

numerical values associated with effects or changes caused by skills

No Comments

No Known Activations