INDEX

Explanations

multiple forms of visual markers or annotations in scientific data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

WebElementEntity

-0.42

 Hayek

-0.42

NewUrlParser

-0.39

이

-0.39

pvp

-0.39

 כן

-0.38

hyrchwyd

-0.38

-0.37

 jeux

-0.37

POSITIVE LOGITS

 SPOT

0.93

 spot

0.86

spot

0.84

Spot

0.82

 Spot

0.82

 spots

0.76

SPOT

0.75

spots

0.72

 Spots

0.68

zero

0.65

Activations Density 0.296%

multiple forms of visual markers or annotations in scientific data

No Comments

No Known Activations

multiple forms of visual markers or annotations in scientific data

No Comments

No Known Activations