INDEX

Explanations

instances where no significant activations occur, indicating a lack of relevant content or patterns in the text

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

脚注の使い方

-0.71

 surla

-0.71

ValueStyle

-0.70

TagMode

-0.69

 typelib

-0.65

"]();

-0.64

 Signalez

-0.64

 isoto

-0.63

 StatefulWidget

-0.63

 MenuView

-0.62

POSITIVE LOGITS

 fondos

0.50

Coordenadas

0.50

 Bartholomew

0.50

ConfigureAwait

0.49

OGND

0.47

ressible

0.47

ďaka

0.45

...

0.45

 almeno

0.45

Välislingid

0.45

Activations Density 0.123%

instances where no significant activations occur, indicating a lack of relevant content or patterns in the text

No Comments

No Known Activations