INDEX

Explanations

legal terminology and case-related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

Amicalement

-0.87

 Мексичка

-0.85

EndProject

-0.71

ratulations

-0.71

noons

-0.70

 iſt

-0.70

extAlignment

-0.70

 betweenstory

-0.70

^(@)

-0.70

 createSprite

-0.70

POSITIVE LOGITS

 argued

0.60

 court

0.56

<eos>

0.52

 Judge

0.51

 contended

0.50

had

0.50

 judge

0.50

 Court

0.48

 concluded

0.46

 judged

0.46

Activations Density 2.130%

legal terminology and case-related phrases

No Comments

No Known Activations