INDEX

Explanations

sequences that involve collecting or aggregating terms or values

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

 purpoſe

-0.58

 pleaſure

-0.53

ConstraintMaker

-0.52

GEBURTSDATUM

-0.52

Personendaten

-0.52

 ſever

-0.51

tvguidetime

-0.51

rungsseite

-0.50

 reaſon

-0.49

 houſe

-0.49

POSITIVE LOGITS

 terms

0.50

 term

0.49

ậc

0.47

 inhoud

0.44

 BorderSide

0.44

świ

0.43

 composants

0.41

terms

0.41

 Term

0.40

 werkzaam

0.40

Activations Density 2.370%

sequences that involve collecting or aggregating terms or values

No Comments

No Known Activations

sequences that involve collecting or aggregating terms or values

No Comments

No Known Activations