INDEX

Explanations

references to academic papers and their authors

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

 Италијани

-0.87

abestanden

-0.86

ItemBackground

-0.84

 propOrder

-0.81

ьаж

-0.80

piram

-0.79

Rohy

-0.77

PerformLayout

-0.76

Autoritní

-0.75

WithIOException

-0.73

POSITIVE LOGITS

fazione

0.41

0.40

ും

0.40

 nostru

0.40

 requestCode

0.40

“

0.39

 textStatus

0.39

formazioni

0.38

󠁿

0.38

 pubblicato

0.38

Activations Density 0.097%

references to academic papers and their authors

No Comments

No Known Activations