INDEX

Explanations

elements related to structured data, typically seen in markup or programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 vectorielles

-0.53

setResizable

-0.52

windowFixed

-0.51

iga

-0.50

цезда

-0.49

ArrowToggle

-0.48

 chaus

-0.46

piecze

-0.46

cul

-0.46

 istore

-0.46

POSITIVE LOGITS

extAlignment

0.85

Personensuche

0.84

 linkovi

0.78

 חיצוניים

0.75

 كومونز

0.74

SequentialGroup

0.71

UnsafeEnabled

0.68

verwijspagina

0.67

 للمعارف

0.67

Diwedd

0.67

Activations Density 0.355%

elements related to structured data, typically seen in markup or programming languages

No Comments

No Known Activations