INDEX

Explanations

references to various divisions or departments, particularly in a legal or organizational context

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

enerbahçe

-0.39

<em>

-0.38

merchant

-0.38

 Darm

-0.37

kur

-0.36

Uhm

-0.36

SEGUIR

-0.36

trä

-0.36

 archeological

-0.36

 prét

-0.35

POSITIVE LOGITS

 division

2.20

 Division

2.14

Division

2.06

division

1.95

 DIVISION

1.86

 divisions

1.84

 Divisions

1.80

DIVISION

1.71

Div

1.71

 divis

1.69

Activations Density 0.125%

references to various divisions or departments, particularly in a legal or organizational context

No Comments

No Known Activations