INDEX

Explanations

data strings in a specific format related to encoding or decoding processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

DockStyle

-0.73

 CanadaChoose

-0.71

RenderAtEndOf

-0.68

MLLoader

-0.66

paramref

-0.61

pecabe

-0.60

 étoient

-0.59

haikusbot

-0.58

 feroit

-0.57

таратура

-0.57

POSITIVE LOGITS

 PyQt

0.33

ger

0.30

料

0.29

 useState

0.28

 отно

0.28

 ${({

0.28

 Photocase

0.27

Gu

0.27

Microkernel

0.27

BASEPATH

0.27

Activations Density 0.307%

data strings in a specific format related to encoding or decoding processes

No Comments

No Known Activations

data strings in a specific format related to encoding or decoding processes

No Comments

No Known Activations