INDEX

Explanations

legal terminology and concepts related to definitions and conditions

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

preceding disclaimers, exceptions, or references

np_acts-logits-general · gemini-2.0-flash

symbols and punctuation

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

 चीज़ों

-1.05

 JpaRepository

-0.98

Tazama

-0.97

featureID

-0.96

Diwedd

-0.95

脚注の使い方

-0.94

Personendaten

-0.94

CloseOperation

-0.93

ValueGenerated

-0.91

GeoNames

-0.91

POSITIVE LOGITS

 transfieras

0.55

 Saltar

0.47

 wirst

0.42

 Перейти

0.41

 sebelumnya

0.39

よ

0.37

 casts

0.36

 المعيارى

0.36

 utafitiHapana

0.36

ſp

0.36

Activations Density 0.942%

legal terminology and concepts related to definitions and conditions

preceding disclaimers, exceptions, or references

symbols and punctuation

No Comments

No Known Activations

legal terminology and concepts related to definitions and conditions

preceding disclaimers, exceptions, or references

symbols and punctuation

No Comments

No Known Activations