INDEX

Explanations

terms related to data streaming and input/output processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Anhalt

-0.86

ایج

-0.83

ngdoc

-0.81

 "..\..\..\

-0.80

@"/

-0.79

 Fawcett

-0.78

QMetaType

-0.78

 Dickinson

-0.77

 pinulongan

-0.77

isRequired

-0.77

POSITIVE LOGITS

 stream

1.43

 streams

1.42

stream

1.38

streams

1.36

 STREAM

1.35

 Stream

1.32

 Streams

1.28

Stream

1.22

STREAM

1.20

Streams

1.08

Activations Density 0.035%

terms related to data streaming and input/output processing

No Comments

No Known Activations