INDEX

Explanations

identifiers and names related to technical or personal entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

fjspx

-0.51

manuelle

-0.51

 cetera

-0.50

ó

-0.49

✭

-0.49

以上就是

-0.48

PLIES

-0.48

Yet

-0.48

 مشين

-0.48

LMAO

-0.47

POSITIVE LOGITS

الحياه

0.66

новниш

0.64

 optique

0.60

 الرياضيه

0.60

 laikā

0.60

bootstrapcdn

0.51

 оригіналу

0.51

 OFDb

0.50

 refroidissement

0.50

 CGRectMake

0.50

Activations Density 2.685%

identifiers and names related to technical or personal entities

No Comments

No Known Activations