INDEX

Explanations

references to complexity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 يتيمه

-0.66

 NSCoder

-0.60

writeField

-0.59

aarrggbb

-0.56

StoryboardSegue

-0.54

Aiheesta

-0.52

 forState

-0.52

hasMoreElements

-0.52

Rüyada

-0.50

 ProtoMessage

-0.49

POSITIVE LOGITS

 Complex

1.13

 complex

1.11

 complexity

1.10

Complex

1.05

 COMPLEX

1.00

 Komplex

1.00

 Complexity

0.97

 complexes

0.95

complex

0.93

 kompleks

0.93

Activations Density 0.123%

references to complexity in various contexts

No Comments

No Known Activations