INDEX

Explanations

opening or introductory phrases in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

StoryboardSegue

-0.79

 '\\;'

-0.78

 EconPapers

-0.77

 InputDecoration

-0.69

Hentet

-0.68

setVerticalGroup

-0.68

Datuak

-0.67

 Italijani

-0.66

็จ

-0.66

rouvez

-0.65

POSITIVE LOGITS

eadilan

0.51

0.50

 anode

0.48

</h3>

0.47

0.45

 Republi

0.44

 schie

0.43

 Púb

0.43

0.42

Activations Density 0.614%

opening or introductory phrases in a document

No Comments

No Known Activations