INDEX

Explanations

references to independent entities or groups

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagext

-0.56

WriteTagHelper

-0.45

 ComVisible

-0.44

 ويكيپيديا

-0.44

ViewFeatures

-0.42

WireFormatLite

-0.39

 Normdatei

-0.39

Derbyniad

-0.39

cabulary

-0.39

ulongan

-0.38

POSITIVE LOGITS

 independent

2.59

independent

2.39

 Independent

2.36

Independent

2.34

 INDEPENDENT

2.13

独立

2.03

 independently

2.02

 independiente

1.96

 independ

1.95

 independence

1.95

Activations Density 0.209%

references to independent entities or groups

No Comments

No Known Activations