INDEX

Explanations

references to clothing and the act of wearing

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

 Normdatei

-0.77

 يتيمه

-0.76

mybatisplus

-0.75

 EconPapers

-0.72

ConstraintMaker

-0.68

Viitteet

-0.67

 kaynağından

-0.66

 Ouverture

-0.65

økt

-0.64

 تضيفلها

-0.64

POSITIVE LOGITS

isome

0.86

 Wear

0.75

Wear

0.68

 wear

0.66

 worn

0.64

ables

0.61

&[

0.60

 wears

0.56

 maso

0.54

wear

0.52

Activations Density 0.033%

references to clothing and the act of wearing

No Comments

No Known Activations