INDEX

Explanations

references to introducing or implementing new concepts or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Waller

-0.51

 dezelve

-0.47

Flammability

-0.45

ubourg

-0.45

Wav

-0.45

 réparation

-0.44

Ehrungen

-0.43

キュリティ

-0.43

Calculating

-0.43

ciphertext

-0.43

POSITIVE LOGITS

 introduction

1.66

 introduce

1.66

 introduces

1.63

 introduced

1.56

 Introduce

1.54

introduce

1.52

 introductions

1.45

Introduce

1.44

 introducing

1.43

 Introdu

1.41

Activations Density 0.131%

references to introducing or implementing new concepts or ideas

No Comments

No Known Activations