INDEX

Explanations

elements of evidence or findings related to legal discussions or judgments

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

Prepositions and articles

np_acts-logits-general · gemini-2.0-flash

supported by substantial evidence

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

 purpoſe

-0.78

 pleaſure

-0.72

 Monfieur

-0.71

Przypisy

-0.71

 myſelf

-0.70

 houſe

-0.68

 ſtre

-0.68

 faſt

-0.67

 تانيه

-0.66

 ſen

-0.66

POSITIVE LOGITS

AsUp

0.80

MigrationBuilder

0.75

InvalidProtocol

0.71

rrggbb

0.71

ьаж

0.68

resave

0.66

kháu

0.65

oa̍t

0.62

 sumpay

0.61

sidemargin

0.58

Activations Density 0.674%

elements of evidence or findings related to legal discussions or judgments

Prepositions and articles

supported by substantial evidence

No Comments

No Known Activations