INDEX

Explanations

references to activity on blogs or online platforms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 nakalista

-1.44

Geplaatst

-1.34

 estekak

-1.31

AddTagHelper

-1.28

Personensuche

-1.26

ⓧ

-1.25

ArrowToggle

-1.20

 незавершена

-1.19

 Roskov

-1.16

 виправивши

-1.15

POSITIVE LOGITS

0.62

0.61

…

0.57

0.55

↵↵

0.52

0.51

re

0.51

”

0.50

Activations Density 0.093%

references to activity on blogs or online platforms

No Comments

No Known Activations