INDEX

Explanations

references to features and specifications of products or items

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



-0.58

قایناق‌لار

-0.53

#+#

-0.49

исленность

-0.48

jewództ

-0.47

 chi̍t

-0.46

BIÉN

-0.44

istoitu

-0.44

verwijspagina

-0.44

Референце

-0.43

POSITIVE LOGITS

 للاسماء

0.47

SequentialGroup

0.40

Ӕ

0.39

plish

0.39

 CreateTagHelper

0.39

CodedInputStream

0.39

IsMutable

0.39

etlen

0.36

 jadx

0.36

 ſeveral

0.36

Activations Density 0.548%

references to features and specifications of products or items

No Comments

No Known Activations