INDEX

Explanations

markup tags and formatting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AsUp

-1.46

хьтан

-1.41

windowFixed

-1.40

 itſelf

-1.36

 ligiloj

-1.36

 <>",

-1.31

 myſelf

-1.30

Efq

-1.29

 ―――――

-1.29

^(@)

-1.27

POSITIVE LOGITS

↵

1.13

1.07

↵↵

1.02

0.94

<eos>

0.84

0.82

0.80

0.79

0.78

Activations Density 0.033%

markup tags and formatting elements

No Comments

No Known Activations