INDEX

Explanations

symbols and formatting tags typically found in code or markup languages

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

HTML formatting tags

np_acts-logits-general · gemini-2.0-flash

formatting and emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 typelib

-0.87

/*

-0.81

 noDo

-0.80

awtextra

-0.78

 Biôgrafia

-0.76

AccessorTable

-0.76

LookAnd

-0.75

<eos>

-0.75

/*

-0.75

 OFDb

-0.72

POSITIVE LOGITS

<u>

0.97

<strong>

0.88

“

0.84

</em>

0.77

‘

0.70

0.67

“…

0.64

bona

0.63

sui

0.63

raison

0.60

Activations Density 0.092%

symbols and formatting tags typically found in code or markup languages

HTML formatting tags

formatting and emphasis

No Comments

No Known Activations