INDEX

Explanations

questions related to data interpretation and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

EDEFAULT

-0.84

 AssemblyCulture

-0.76

bewerken

-0.72

 Normdatei

-0.72

GIVEREF

-0.71

setVerticalGroup

-0.69

 >=",

-0.64

 Administrativna

-0.63

 Vikipedi

-0.63

POSITIVE LOGITS

 esimer

0.57

 bağı

0.52

 permanently

0.51

vraagd

0.48

 creș

0.48

 orejas

0.48

¶

0.47

 menyem

0.47

 Horv

0.45

 cử

0.45

Activations Density 0.172%

questions related to data interpretation and analysis

No Comments

No Known Activations