INDEX

Explanations

references to historical events and figures

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

rungsseite

-0.67

enumi

-0.61

PreferredItem

-0.60

<tfoot>

-0.58

 AspNetCore

-0.57

 متعلقه

-0.55

__(/*!

-0.55

UserScript

-0.54

 &___

-0.54

AHL

-0.54

POSITIVE LOGITS

 infamous

0.73

 Operation

0.69

 '\\;'

0.66

Operation

0.58

 peristiwa

0.56

 événements

0.56

 tragé

0.56

 fateful

0.55

events

0.55

 Battle

0.53

Activations Density 0.484%

references to historical events and figures

No Comments

No Known Activations