INDEX

Explanations

references to machine learning model operations and errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

derung

-0.38

 arru

-0.36

 Recursos

-0.35

 photographers

-0.35

 fieldNum

-0.35

förderung

-0.35

riedenheit

-0.35

 task

-0.34

Photographer

-0.34

μού

-0.34

POSITIVE LOGITS

GTCX

0.66

 nakalista

0.63

invokeLater

0.60

awtextra

0.57

 autorytatywna

0.57

 intptr

0.56

 EconPapers

0.56

 typelib

0.54

MLLoader

0.50

reportWebVitals

0.50

Activations Density 0.385%

references to machine learning model operations and errors

No Comments

No Known Activations