INDEX

Explanations

references to health or cosmetic treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 <<<<<<<<<<<<<<

-0.64

UnsafeEnabled

-0.62

 autorytatywna

-0.61

hyrchwyd

-0.60

AsUp

-0.59

BagLayout

-0.58

ineno

-0.58

]")]

-0.57

RTLI

-0.57

 JpaRepository

-0.56

POSITIVE LOGITS

 reps

0.59

setCount

0.55

 Reps

0.52

Reps

0.51

 تانيه

0.50

 endpoint

0.49

 feedback

0.48

 grazia

0.48

ercizi

0.48

rep

0.47

Activations Density 0.256%

references to health or cosmetic treatments

No Comments

No Known Activations