INDEX

Explanations

references to the concept of "no" or its variations, signifying absence or negation

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-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

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

IMPORTED

-0.62

AutoField

-0.56

NewUrlParser

-0.54

nass

-0.54

plotlib

-0.53

ranath

-0.51

rxjs

-0.51

EndInit

-0.51

ISPR

-0.50

ffindor

-0.50

POSITIVE LOGITS

发表于

0.52

 مشين

0.52

 arşivlendi

0.51

 BoxDecoration

0.50

WriteLiteral

0.50

adə

0.50

 depositphotos

0.48

ês

0.47

 Himo

0.46

 flyknit

0.46

Activations Density 0.147%

references to the concept of "no" or its variations, signifying absence or negation

No Comments

No Known Activations