INDEX

Explanations

possessive pronouns and terms indicating relationships or connections between individuals

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

λιο

-0.52

 recev

-0.46

 handleMessage

-0.45

 involved

-0.42

่วย

-0.42

échelle

-0.42

נית

-0.42

boten

-0.41

yntaxException

-0.41

 مواليد

-0.41

POSITIVE LOGITS

RegistryLite

0.94

原始内容存档于

0.79

 متعلقه

0.70

numerusform

0.68

 محفوظة

0.66

IRQn

0.64

principalColumn

0.64

interopRequire

0.63

 suya

0.63

 שוליים

0.63

Activations Density 0.186%

possessive pronouns and terms indicating relationships or connections between individuals

No Comments

No Known Activations