INDEX

Explanations

elements and attributes used in programming, particularly those related to IDs and strings in queries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

setzer

-0.47

{},

-0.47

}}}

-0.46

ligere

-0.46

zulegen

-0.45

(&:

-0.44

Izvori

-0.44

 افتراض

-0.43

SharedDtor

-0.43

"]["

-0.42

POSITIVE LOGITS

 starts

1.48

 beginning

1.46

 begins

1.40

 Starts

1.38

 starting

1.37

 ending

1.36

begins

1.29

 Starting

1.29

 Begins

1.29

Starting

1.26

Activations Density 0.292%

elements and attributes used in programming, particularly those related to IDs and strings in queries

No Comments

No Known Activations