INDEX

Explanations

references to specific samples and their characteristics in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

↵↵

-0.58

 deal

-0.53

ernalia

-0.53

 DIAL

-0.53

kozások

-0.53

 informe

-0.52

verk

-0.52

 peran

-0.51

тельность

-0.51

[['

-0.49

POSITIVE LOGITS

Efq

0.78

 Monfieur

0.69

 oprot

0.60

NSIndexPath

0.60

 MonoBehaviour

0.59

 getItemCount

0.57

 <>",

0.57

ToDelete

0.56

 ExecuteAsync

0.56

IntoConstraints

0.55

Activations Density 0.939%

references to specific samples and their characteristics in a scientific context

No Comments

No Known Activations