INDEX

Explanations

concepts related to ulterior motives and manipulative intentions

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

inguém

-0.56

tagna

-0.55

QtCore

-0.52

 mignon

-0.51

 humility

-0.50

 secco

-0.50

lexia

-0.48

 runnable

-0.48

払

-0.47

 normalcy

-0.47

POSITIVE LOGITS

Hentet

0.66

UnusedPrivate

0.64

loit

0.55

Архівовано

0.55

 Профиль

0.54

 secretly

0.53

WriteLiteral

0.52

Parcelize

0.51

 насељу

0.51

 greedy

0.49

Activations Density 0.450%

concepts related to ulterior motives and manipulative intentions

No Comments

No Known Activations