INDEX

Explanations

references to specific projects or accomplishments

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

 Monfieur

-0.43

 Jefus

-0.37

 Inscrivez

-0.36

 corde

-0.35

 Dés

-0.35

 houſe

-0.35

 Perfon

-0.33

 Diſ

-0.33

 ſta

-0.33

 Inſ

-0.33

POSITIVE LOGITS

Vidite

0.64

новништво

0.59

脚注の使い方

0.52

 inevitable

0.52

лтамалар

0.52

 Paglinawan

0.52

 inevitably

0.50

thâu

0.49

NUMX

0.48

__(/*!

0.47

Activations Density 0.510%

references to specific projects or accomplishments

No Comments

No Known Activations