INDEX

Explanations

references to programming and technology-related content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

XmlEnum

-0.51

iedad

-0.47

 AspNetCore

-0.46

avadoc

-0.44

مو

-0.44

LayoutPanel

-0.42

ned

-0.42

itele

-0.41

bitField

-0.40

ху

-0.40

POSITIVE LOGITS

 тоже

1.36

 also

1.26

 също

1.18

also

1.16

too

1.14

 likewise

1.14

 similarly

1.13

も同じ

1.12

 ebenfalls

1.12

 också

1.10

Activations Density 0.833%

references to programming and technology-related content

No Comments

No Known Activations