INDEX

Explanations

locations or contexts within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

entary

-0.57

Schwarz

-0.56

 Mémoire

-0.55

 dõi

-0.54

manteau

-0.52

 Schwarz

-0.52

érables

-0.51

 Funcion

-0.51

 nors

-0.51

 Chasse

-0.51

POSITIVE LOGITS

 NSCoder

0.73

KommentareTeilen

0.67

RegistryLite

0.66

Initializable

0.66

脚注の使い方

0.63

 beginnetje

0.58

 BoxFit

0.57

ViewFeatures

0.57

LabelTagHelper

0.57

 ngoài

0.56

Activations Density 0.143%

locations or contexts within the text

No Comments

No Known Activations