INDEX

Explanations

patterns of whitespace or formatting in the text

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

Hexadecimal byte values

np_acts-logits-general · gemini-2.0-flash

computing start markers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

inty

-0.50

↵↵

-0.47

Ď

-0.46

 Volkes

-0.44

 suitable

-0.43

isela

-0.43

𝐠

-0.43

 essentially

-0.42

 absolutely

-0.42

Very

-0.41

POSITIVE LOGITS

<bos>

3.29

’

1.30

1.24

 виправивши

1.17

 Савезне

1.15

 disambiguazione

1.07

 Paglinawan

1.06

хьтан

1.05

 Baillargeon

1.04

Diwedd

0.97

Activations Density 0.002%

patterns of whitespace or formatting in the text

Hexadecimal byte values

computing start markers

No Comments

No Known Activations