INDEX

Explanations

phrases related to covert operations and hidden structures

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

Népesség

-0.73

 useAppContext

-0.70

 الحره

-0.68

 وتسجيلات

-0.68

AndEndTag

-0.68

 resourceCulture

-0.68

Personendaten

-0.66

ništ

-0.66

InputBorder

-0.66

%");

-0.66

POSITIVE LOGITS



0.51

:✨

0.48

TryGetValue

0.47

出版年

0.47

ządz

0.43

IANGLES

0.42

 where

0.41

 OFDb

0.41

 Мексичка

0.39

hoz

0.39

Activations Density 0.648%

phrases related to covert operations and hidden structures

No Comments

No Known Activations