INDEX

Explanations

information related to cookie usage and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

MemoryWarning

-0.62

 resourceCulture

-0.62

tvguidetime

-0.55

новниш

-0.52



-0.51

URLException

-0.51

Bioaccumulative

-0.51

/**

-0.50

UserScript

-0.50

الحياه

-0.49

POSITIVE LOGITS

 read

1.48

 learn

1.38

 Learn

1.36

Learn

1.36

 Read

1.30

 click

1.28

learn

1.28

 Click

1.27

Click

1.21

read

1.18

Activations Density 0.185%

information related to cookie usage and privacy policies

No Comments

No Known Activations