INDEX

Explanations

references to shadows in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<eos>

-0.67

-0.53

-0.52

rs

-0.51

-0.49

//

-0.48

And

-0.47

va

-0.46

POSITIVE LOGITS

 Houſe

1.33

 myſelf

1.29

 pleaſure

1.26

 houſe

1.26

 Majefty

1.23

 ſever

1.22

 photolibrary

1.22

 itſelf

1.19

 leſs

1.16

 Diſ

1.15

Activations Density 0.163%

references to shadows in various contexts

No Comments

No Known Activations