INDEX

Explanations

references to large quantities or amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

idalgo

-0.77

']))

-0.76

orene

-0.63

esinde

-0.61

 FUND

-0.60

⎦

-0.60

 nhàng

-0.60

textsc

-0.59

wasi

-0.59

RefNanny

-0.59

POSITIVE LOGITS

 فريبيس

0.76

WithIOException

0.75

Autoritní

0.73

DeleteBehavior

0.71

ecap

0.68

ViewById

0.66

 EconPapers

0.64

 Infórmanos

0.64

вЂ

0.63

 utafitiHapana

0.62

Activations Density 0.192%

references to large quantities or amounts

No Comments

No Known Activations