INDEX

Explanations

phrases related to legal and regulatory actions

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

followed by "in" or location words

np_acts-logits-general · gemini-2.0-flash

legal proceedings, events, or outcomes

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

findpost

-1.02

 للاسماء

-0.90

Efq

-0.89

 myſelf

-0.88

 ་་

-0.86

ContentAsync

-0.85

 wikipagina

-0.84

 feroit

-0.80

AnchorStyles

-0.79

 ThemeData

-0.79

POSITIVE LOGITS

1.31

‘

1.27

‘

0.80

«

0.75

 govt

0.75

’

0.74

…

0.72

0.71

 amid

0.70

</h1>

0.69

Activations Density 0.174%

phrases related to legal and regulatory actions

followed by "in" or location words

legal proceedings, events, or outcomes

No Comments

No Known Activations