INDEX

Explanations

negative and positive indicators or signs within a context, likely related to network or system state changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

nodoc

-0.59

openqa

-0.52

EnableWeb

-0.50

blico

-0.49

PyExc

-0.49

 """",

-0.49

ciaal

-0.48

canActivate

-0.48

 Bescheid

-0.48

 VIDEOT

-0.47

POSITIVE LOGITS

 виправивши

1.20

VersionUID

0.80

Tembelea

0.78

sizeCache

0.78

帖最后由

0.74

expandindo

0.72

 VIAF

0.72

 Normdatei

0.69

دانشنامهٔ

0.69

UnsafeEnabled

0.69

Activations Density 0.091%

negative and positive indicators or signs within a context, likely related to network or system state changes

No Comments

No Known Activations