INDEX

Explanations

references to specific programming constructs or functions related to data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 kaarangay

-1.68

 Paglinawan

-1.68

 Савезне

-1.67

Autoritní

-1.66

 Roskov

-1.56

WithIOException

-1.54

 betweenstory

-1.50

<bos>

-1.47

GEBURTSDATUM

-1.43

 autorytatywna

-1.42

POSITIVE LOGITS

0.78

0.73

0.72

is

0.71

0.70

 also

0.68

in

0.63

0.60

and

0.59

Activations Density 21.444%

references to specific programming constructs or functions related to data structures

No Comments

No Known Activations