INDEX

Explanations

general negations and emphatic expressions

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

Personensuche

-1.48

 الرياضيه

-0.97

LookAnd

-0.85

 виправивши

-0.82

verifyException

-0.81

 invokingState

-0.78

MarshalTo

-0.77

ArgsConstructor

-0.74

 nahilalakip

-0.72

Personendaten

-0.72

POSITIVE LOGITS

got

0.56

agin

0.52

0.47

ndal

0.47

du

0.45

 MonoBehaviour

0.41

Gar

0.41

hle

0.40

 ща

0.40

PRIMARY

0.39

Activations Density 0.165%

general negations and emphatic expressions

No Comments

No Known Activations