INDEX

Explanations

document boundaries and structural markers that indicate new sections in mixed code and formal text content

oai_token-act-pair · o3-mini Triggered by @yemengyus1

various types of punctuation marks and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

↵

-1.39

↵↵

-1.19

-1.13

-1.02

-1.01

-0.99

-0.94

//

-0.91

-0.88

-0.85

POSITIVE LOGITS

^(@)

1.30

ſelves

1.25

 itſelf

1.23

<bos>

1.22

 pleaſure

1.20

BibitemShut

1.18

 iſt

1.17

 myſelf

1.17

 purpoſe

1.16

 reaſon

1.15

Activations Density 1.267%

document boundaries and structural markers that indicate new sections in mixed code and formal text content

various types of punctuation marks and symbols

No Comments

No Known Activations