INDEX

Explanations

statements that affirm or emphasize a point

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

@"/

-0.34

Похо

-0.33

CreateModel

-0.32

帖最后由

-0.31

addPreferredGap

-0.31

adaptiveStyles

-0.28

 initial

-0.27

setPref

-0.27

 Sito

-0.27

POSITIVE LOGITS

eraard

1.32

 natürlich

1.28

 Natürlich

1.27

følgelig

1.27

 natuurlijk

1.23

verständlich

1.22

Naturally

1.20

 Naturally

1.19

Natürlich

1.16

 naturalmente

1.16

Activations Density 0.138%

statements that affirm or emphasize a point

No Comments

No Known Activations