INDEX

Explanations

discussions around computational challenges and algorithms related to dimensionality and feature selection

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

genöss

-0.30

les

-0.29

 quarter

-0.29

mal

-0.28

ARGUMENT

-0.28

ướt

-0.28

ReturnValue

-0.28

ładka

-0.28

 regel

-0.28

ad

-0.28

POSITIVE LOGITS

 impractica

0.72

UrlResolution

0.66

 kasarigan

0.63

Parcelize

0.63

 виправивши

0.62

 snippetHide

0.61

findpost

0.60

richTextPanel

0.60

 unsustainable

0.59

 GenerationType

0.59

Activations Density 0.845%

discussions around computational challenges and algorithms related to dimensionality and feature selection

No Comments

No Known Activations