INDEX

Explanations

references to specific publications, authors, or components related to scientific or medical research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 câte

-0.45

 gewöhnlich

-0.39

oč

-0.37

 Namens

-0.36

 Trabajo

-0.36

 jiwa

-0.36

 TRABAJO

-0.35

 cubiertos

-0.35

 Puedes

-0.34

 ajustable

-0.34

POSITIVE LOGITS

 ModelExpression

1.07

UrlResolution

0.96

Hochspringen

0.86

WireFormatLite

0.85

GraphicsUnit

0.84

expandindo

0.83

 Infórmanos

0.82

 MainAxisSize

0.80

LookAnd

0.79

 betweenstory

0.78

Activations Density 0.716%

references to specific publications, authors, or components related to scientific or medical research

No Comments

No Known Activations