INDEX

Explanations

references to programming concepts and errors

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 utafitiHapana

-0.65

uxxxx

-0.57

 themſelves

-0.54

 continúas

-0.54

Aiheesta

-0.53

Eſ

-0.53

 itſelf

-0.53

 raiſ

-0.51

 surla

-0.51

 ſur

-0.51

POSITIVE LOGITS

RUnlock

0.57

IUrlHelper

0.57

NOPQRST

0.43

libft

0.41

nloa

0.40

arrhea

0.40

getColumnIndex

0.40

 pinulongan

0.40

TargetException

0.39

ollectionView

0.39

Activations Density 1.587%

references to programming concepts and errors

No Comments

No Known Activations