INDEX

Explanations

structured data formats, especially those related to code or configuration

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

Code snippets or code-related text

np_acts-logits-general · gemini-2.0-flash

code examples and programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

</em>

-0.52

hasMoreElements

-0.51

__*/

-0.51

Nab

-0.47

))]

-0.45

}}}{

-0.45

țiune

-0.45

stini

-0.45

[['

-0.45

 always

-0.45

POSITIVE LOGITS

Hauptartikel

0.76

CloseOperation

0.76

 houſe

0.66

ValueStyle

0.65

loài

0.65

SEGUIR

0.65

 مرئيه

0.64

spesies

0.63

ſelves

0.63

 ſche

0.61

Activations Density 0.007%

structured data formats, especially those related to code or configuration

Code snippets or code-related text

code examples and programming languages

No Comments

No Known Activations