INDEX

Explanations

references to the prefix "Ph" or terms related to phenomena or subjects beginning with "Ph"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Externí

-0.59

 volontaire

-0.55

forChild

-0.55

 dentaire

-0.53

Xna

-0.52

 Bress

-0.52

Revenir

-0.50

kita

-0.50

lasia

-0.50

DeleteBehavior

-0.49

POSITIVE LOGITS

IntoConstraints

0.55

енча

0.52

SuspendLayout

0.52

esModule

0.51

AllAfrica

0.51

RenderAtEndOf

0.49

 Normdatei

0.49

CWE

0.48

Geplaatst

0.46

OTO

0.45

Activations Density 0.184%

references to the prefix "Ph" or terms related to phenomena or subjects beginning with "Ph"

No Comments

No Known Activations