INDEX

Explanations

instances of significant actions or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

labelledby

-0.64

 africaine

-0.61

 LCCN

-0.58

waitKey

-0.57

 kılıf

-0.55

 MessageBoxIcon

-0.55

 tué

-0.54

الحياه

-0.54

 sanguí

-0.52

 mapStateToProps

-0.52

POSITIVE LOGITS

 Réponses

0.68

SBATCH

0.58

elan

0.54

IntOverflow

0.51

iastical

0.49

andinavia

0.49

ilitation

0.48

etsu

0.48

crollView

0.48

 down

0.48

Activations Density 0.532%

instances of significant actions or concepts

No Comments

No Known Activations