INDEX

Explanations

instances of formatting or section headings in text

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

 Paglinawan

-1.33

 myſelf

-1.25

 itſelf

-1.20

 Theſe

-1.19

 becauſe

-1.18

 Reſ

-1.18

 Anſ

-1.16

Eſ

-1.14

 Beſ

-1.11

Efq

-1.11

POSITIVE LOGITS

0.96

↵

0.89

0.88

<eos>

0.86

0.78

0.77

0.76

0.75

in

0.73

is

0.73

Activations Density 0.052%

instances of formatting or section headings in text

No Comments

No Known Activations