INDEX

Explanations

terms related to legal processes and hearings

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

rehearing and revised documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

GetMapping

-0.32

Ode

-0.28

pas

-0.27

Abp

-0.27

now

-0.27

Ep

-0.27

Ep

-0.26

Now

-0.26

Lud

-0.25

 invitamos

-0.25

POSITIVE LOGITS

 revised

1.59

revised

1.30

 revise

1.29

 Revised

1.28

 revision

1.23

Revised

1.22

 revising

1.18

 revisions

1.12

 Revision

1.10

revision

0.91

Activations Density 0.001%

terms related to legal processes and hearings

rehearing and revised documents

No Comments

No Known Activations