INDEX

Explanations

numerical identifiers and references, particularly in academic or research contexts

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

 indígen

-0.72

 unſer

-0.71

 beſch

-0.71

 zwiſchen

-0.70

 imagui

-0.69

 ſeines

-0.68

<unused23>

-0.68

<unused79>

-0.68

<unused52>

-0.68

<unused14>

-0.68

POSITIVE LOGITS

<bos>

0.46

TagMode

0.36

cshtml

0.33

bewerken

0.30

WebpackPlugin

0.29

 noDo

0.28

makeatother

0.27

errHandler

0.27

 EconPapers

0.26

Activations Density 0.065%

numerical identifiers and references, particularly in academic or research contexts

No Comments

No Known Activations