INDEX

Explanations

technical keywords and syntax from programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

moveToFirst

-0.53

RectangleBorder

-0.53

PrototypeOf

-0.48

selaer

-0.47

QApplication

-0.46

 Brutus

-0.46

teria

-0.46

Siddhartha

-0.45

rosophila

-0.45

isticated

-0.45

POSITIVE LOGITS

 CreateTagHelper

0.66

省市镇

0.64

 unknownFields

0.63

emples

0.62

 transférez

0.61

schirm

0.55

 betweenstory

0.55

 disponibilités

0.52

 resourceCulture

0.51

Personensuche

0.51

Activations Density 0.360%

technical keywords and syntax from programming or coding contexts

No Comments

No Known Activations