INDEX

Explanations

comments and documentation in code, focusing on instructions and notes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glEnd

-0.70

parsedMessage

-0.67

TestingModule

-0.62

 awakeFromNib

-0.61

 LoginForm

-0.61

PositiveButton

-0.61

 dAtA

-0.58

createCanvas

-0.57

 makl

-0.56

endforeach

-0.56

POSITIVE LOGITS

脚注の使い方

0.76

oa̍t

0.63

GEBURTS

0.57

owanego

0.57

enumi

0.56

 disponibilités

0.56

Espèce

0.56

verwijspagina

0.55

 hago

0.54

owanej

0.53

Activations Density 0.605%

comments and documentation in code, focusing on instructions and notes

No Comments

No Known Activations