INDEX

Explanations

references to the term "Kin" and its variations in contexts related to products or people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

okovic

-0.64

sistor

-0.52

 Tengah

-0.52

외부

-0.52

 Paglinawan

-0.52

นะนำ

-0.52

ABASES

-0.51

 Infórmanos

-0.50

RepeatedField

-0.50

way

-0.50

POSITIVE LOGITS

تقاوى

0.62

ftagPool

0.61

InlineData

0.58

gonic

0.55

styleable

0.55

cin

0.54

 nemen

0.53

yet

0.53

 rest

0.52

Portail

0.52

Activations Density 0.110%

references to the term "Kin" and its variations in contexts related to products or people

No Comments

No Known Activations