INDEX

Explanations

structured code elements and syntax

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

Code snippets and programming terms

np_acts-logits-general · gemini-2.0-flash

code structure and closing braces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

^(@)

-1.26

Efq

-1.17

>\<^

-1.12

 ་་

-1.11

ientras

-1.04

 myſelf

-1.04

 ―――――

-1.02

\\

-1.01

〢

-1.00

\<^

-0.98

POSITIVE LOGITS

<eos>

1.18

1.12

}}

0.88

</em>

0.87

...

0.85

0.84

0.81

…

0.81

</code>

0.77

...

0.76

Activations Density 0.218%

structured code elements and syntax

Code snippets and programming terms

code structure and closing braces

No Comments

No Known Activations