INDEX

Explanations

technical terms and references related to scientific studies and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.74

classnames

-0.62

ftagPool

-0.61

WireFormatLite

-0.60

 Hän

-0.60

resser

-0.57

 Réponses

-0.57

parsedMessage

-0.57

 plaats

-0.56

Ngb

-0.56

POSITIVE LOGITS

esModule

0.64

EditorBrowsable

0.63

tagHelperRunner

0.57

IUrlHelper

0.56

]";

0.53

Bước

0.53

=?";

0.53

%";

0.51

=";

0.49

mAuth

0.49

Activations Density 1.666%

technical terms and references related to scientific studies and functions

No Comments

No Known Activations