INDEX

Explanations

elements related to legal terminology and case references

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

Precedes a variety of symbols, letters and numbers

np_acts-logits-general · gemini-2.0-flash

give, fact, on, his, $

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

########.

-0.74

EndGlobalSection

-0.58

+#+

-0.53

OGND

-0.53

RenderAtEndOf

-0.52

RegressionTest

-0.52

 للمعارف

-0.51

 paradox

-0.50

 discontinuity

-0.49

settling

-0.47

POSITIVE LOGITS

MethodManager

0.36

selben

0.33

 تانيه

0.32

 Wikiseite

0.31

tiken

0.31

('../../

0.30

faßt

0.30

 nothwendig

0.30

cplusplus

0.30

 organisations

0.29

Activations Density 0.053%

elements related to legal terminology and case references

Precedes a variety of symbols, letters and numbers

give, fact, on, his, $

No Comments

No Known Activations