INDEX

Explanations

numerical data and sequences

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

iodía

-0.47

 LEYENDO

-0.47

 hänen

-0.45

ípio

-0.43

unteering

-0.43

resume

-0.42

 résumé

-0.42

lewati

-0.42

 rework

-0.41

Discus

-0.41

POSITIVE LOGITS

+#+

0.50

centralwidget

0.49

etc

0.48

routeProvider

0.47

etc

0.46

labelledby

0.46

getValueAt

0.46

 deleteById

0.46

ValueStyle

0.45

AutoScaleMode

0.44

Activations Density 0.361%

numerical data and sequences

No Comments

No Known Activations