INDEX

Explanations

technical discussions about errors and troubleshooting in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 fascinating

-0.35

 vær

-0.32

Trama

-0.31

 inspiration

-0.30

 greatness

-0.30

senz

-0.29

 parado

-0.28

 luscious

-0.28

Snapshots

-0.28

 uncanny

-0.28

POSITIVE LOGITS

SourceChecksum

0.69

aarrggbb

0.64

 tartalomajánló

0.63

RenderAtEndOf

0.63

CloseOperation

0.62

 defStyle

0.62

 CiNii

0.61

fjspx

0.60

richTextPanel

0.60

AndEndTag

0.60

Activations Density 0.024%

technical discussions about errors and troubleshooting in programming

No Comments

No Known Activations