INDEX

Explanations

HTML and script elements within the code

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

</body></html>

np_acts-logits-general · gemini-2.0-flash

closing html body tag

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

ectoria

-0.65

Carriera

-0.64

########.

-0.60

Życiorys

-0.59

LabelTagHelper

-0.57

+#+#

-0.56

 EconPapers

-0.56

 BoxFit

-0.55

المناصب

-0.54

AddTagHelper

-0.54

POSITIVE LOGITS

endsection

0.71

expandindo

0.69

')";

0.61

serviceWorker

0.57

footer

0.56

'};

0.56

 scripts

0.56

"}";

0.55

scripts

0.55

 footer

0.55

Activations Density 0.074%

HTML and script elements within the code

</body></html>

closing html body tag

No Comments

No Known Activations