INDEX

Explanations

expressions related to self-discovery and personal growth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 themselves

-0.54

กัน

-0.53

 meille

-0.51

 leyendas

-0.51

 theirs

-0.51

 their

-0.50

their

-0.50

 kullanılan

-0.48

 gants

-0.48

 nobis

-0.48

POSITIVE LOGITS

ArgsConstructor

0.92

 NSCoder

0.90

RenderAtEndOf

0.82

BeginInit

0.81

ChildScrollView

0.72

 AssemblyCompany

0.72

AnchorStyles

0.71

 myself

0.70

 виправивши

0.67

 numberWith

0.67

Activations Density 0.406%

expressions related to self-discovery and personal growth

No Comments

No Known Activations