INDEX

Explanations

references to variables and mathematical notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ་་

-1.14

)");

-1.08

 ―――――

-1.05

"):

-0.98

">😂

-0.94

}%

-0.93

 Theſe

-0.92

)”.

-0.92

 Beſ

-0.90

)";

-0.90

POSITIVE LOGITS

1.32

1.30

1.27

1.23

1.21

1.20

1.19

1.18

Activations Density 1.624%

references to variables and mathematical notation

No Comments

No Known Activations