INDEX

Explanations

references to complexity or intricate systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 AssemblyCulture

-0.79

 CreateTagHelper

-0.75

Personendaten

-0.74

tvguidetime

-0.71

IntoConstraints

-0.68

SourceChecksum

-0.67

TypedDataSet

-0.67

WebElementEntity

-0.64

stdc

-0.63

ImageContext

-0.61

POSITIVE LOGITS

 complex

2.88

complex

2.63

 Complex

2.53

 complicated

2.47

Complex

2.47

 COMPLEX

2.43

 complexe

2.24

COMPLEX

2.13

 complexity

2.05

 complexes

2.02

Activations Density 0.150%

references to complexity or intricate systems

No Comments

No Known Activations