INDEX

Explanations

terms and phrases related to charts and graphs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

gın

-0.38

المناصب

-0.37

 Almost

-0.36

didSet

-0.35

Almost

-0.35

Servus

-0.35

few

-0.34

nons

-0.34

 common

-0.33

Naissance

-0.33

POSITIVE LOGITS

 chart

1.94

 Chart

1.80

 charts

1.76

chart

1.73

Chart

1.70

 Charts

1.61

CHART

1.52

 CHART

1.49

Charts

1.45

 diagram

1.42

Activations Density 0.385%

terms and phrases related to charts and graphs

No Comments

No Known Activations

terms and phrases related to charts and graphs

No Comments

No Known Activations