INDEX

Explanations

numeric values associated with property features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 rhestr

-0.71

InputBorder

-0.69

twimg

-0.64

Билгалдахарш

-0.63

 Paglinawan

-0.61

 Participant

-0.60

 صوتيه

-0.58

χεία

-0.58

 Partici

-0.57

rir

-0.57

POSITIVE LOGITS

 bedrooms

0.55

tencent

0.51

 kautta

0.50

 aDecoder

0.48

Бахар

0.48

 slaap

0.47

minecraft

0.47

 föld

0.47

 löytyy

0.47

getRuntime

0.47

Activations Density 0.048%

numeric values associated with property features

No Comments

No Known Activations