INDEX

Explanations

phrases describing adequacy or appropriateness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Datuak

-0.45

}{|

-0.42

 Ceremon

-0.41

rungsseite

-0.39

 SIMON

-0.39

-0.38

 trow

-0.37

 Commercial

-0.36

 proto

-0.36

 resourceCulture

-0.36

POSITIVE LOGITS

 при

0.86

 przy

0.60

 desmotivaciones

0.57

suitable

0.56

 suitable

0.54

addContainerGap

0.54

Rs

0.51

RegressionTest

0.50

 IBOutlet

0.50

При

0.49

Activations Density 0.243%

phrases describing adequacy or appropriateness

No Comments

No Known Activations