INDEX

Explanations

technical terms and notation related to programming or software development

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

 autorytatywna

-0.72

 propOrder

-0.65

Personendaten

-0.62

ContentAsync

-0.60

rungsseite

-0.54

лтамалар

-0.53

StructEnd

-0.53

 Chwiliwch

-0.52

 ModelExpression

-0.51

AndEndTag

-0.51

POSITIVE LOGITS

html

0.40

$.

0.39

ensatz

0.36

 jaket

0.36

 Criminal

0.35

 Metropolitan

0.35

 Najib

0.34

 Trost

0.34

 Prasad

0.34

Activations Density 0.373%

technical terms and notation related to programming or software development

No Comments

No Known Activations