INDEX

Explanations

visual representations of data and analyses, particularly diagrams and flow charts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

hasMoreElements

-0.55

حياتها

-0.50

antMatchers

-0.47

gatsby

-0.47

 outstanding

-0.45

HttpServlet

-0.45

nicki

-0.44

 bains

-0.44

ustu

-0.44

omento

-0.43

POSITIVE LOGITS

 diagram

1.45

 diagrams

1.31

 chart

1.28

 charts

1.21

map

1.21

diagram

1.21

 Diagram

1.15

 maps

1.11

 DIAGRAM

1.07

 Diagrams

1.06

Activations Density 0.639%

visual representations of data and analyses, particularly diagrams and flow charts

No Comments

No Known Activations