INDEX

Explanations

references to catalog numbers and accession details

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

"]();

-0.74

]");

-0.63

'));

-0.63

"));

-0.63

"]

-0.62

)";

-0.60

EndInit

-0.59

 ''),

-0.59

]]

-0.59

]);

-0.59

POSITIVE LOGITS

 number

1.20

 Number

1.14

No

1.03

№

1.03

Number

1.02

 NUMBER

1.02

number

0.97

№

0.96

NUMBER

0.94

Nr

0.93

Activations Density 0.326%

references to catalog numbers and accession details

No Comments

No Known Activations