INDEX

Explanations

specific programming constructs or annotations within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 beginnetje

-1.06

principalTable

-0.98

LookAnd

-0.98

 ModelExpression

-0.97

 kaarangay

-0.97

aarrggbb

-0.96

SourceChecksum

-0.96

Personensuche

-0.95

 оригіналу

-0.93

تقاوى

-0.92

POSITIVE LOGITS

ʒ

0.42

 onCreateView

0.41

Permalink

0.38

Swag

0.38

Bam

0.38

endforeach

0.38

ning

0.37

Unmarshaller

0.37

 hại

0.37

ラム

0.37

Activations Density 0.094%

specific programming constructs or annotations within code

No Comments

No Known Activations