INDEX

Explanations

specific company names and related entities in a legal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/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.33.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

 Werkstatt

-0.29

 crun

-0.28

estría

-0.26

 étoient

-0.26

 contigo

-0.25

ándola

-0.25

hot

-0.25

 Lös

-0.25

 lhes

-0.24

ordnung

-0.24

POSITIVE LOGITS

ंदीखरीदारी

0.96

KommentareTeilen

0.94

 estekak

0.91

 informée

0.88

rungsseite

0.88

AddTagHelper

0.85

⪜

0.85

StoryboardSegue

0.84

 AssemblyCompany

0.81

SequentialGroup

0.81

Activations Density 0.575%

specific company names and related entities in a legal context

No Comments

No Known Activations