INDEX

Explanations

quantitative representations of numbers and measures

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

es

-0.77

-0.71

-0.70

def

-0.70

 Orrell

-0.68

def

-0.66

-0.62

?>">

-0.62

SQLException

-0.60

POSITIVE LOGITS

 eighty

1.02

 seventy

0.97

 Ninety

0.96

 ninety

0.96

 cinquante

0.95

 ſmall

0.95

 sixty

0.94

 ſeveral

0.93

ousands

0.93

 Theſe

0.93

Activations Density 0.171%

quantitative representations of numbers and measures

No Comments

No Known Activations