INDEX

Explanations

references to various types of apparatus

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

apparatus

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

 Immig

-0.49

Kill

-0.48

Hochspringen

-0.48

gecko

-0.48

Wi

-0.48

<tr>

-0.47

kills

-0.47

 Oncology

-0.47

 estekak

-0.47

Pink

-0.47

POSITIVE LOGITS

 apparatus

2.17

 Apparatus

2.03

Apparatus

1.81

 APPARATUS

1.76

 aparato

1.25

aratus

1.20

 appar

1.18

PARATUS

1.13

 aparatos

1.09

appareil

1.02

Activations Density 0.008%

references to various types of apparatus

apparatus

No Comments

No Known Activations

references to various types of apparatus

apparatus

No Comments

No Known Activations