INDEX

Explanations

references to historical figures and their associated locations or properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

BagLayout

-0.42

ChildScrollView

-0.42

 Tuch

-0.40

RectangleBorder

-0.40

AntiForgeryToken

-0.39

calientes

-0.39

 parole

-0.39

LabelTagHelper

-0.38

Népesség

-0.37

unzel

-0.37

POSITIVE LOGITS

 shingle

0.54

 Seal

0.53

 seals

0.52

 Haven

0.52

RN

0.50

 Needles

0.50

 cliff

0.47

 Goodwin

0.47

Haven

0.46

 seal

0.46

Activations Density 0.333%

references to historical figures and their associated locations or properties

No Comments

No Known Activations