INDEX

Explanations

keywords related to graphical user interface elements and their manipulation

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

 numerus

-0.56

 يتيمه

-0.52

ziek

-0.51

وار

-0.48

writeByte

-0.48

 period

-0.48

bietern

-0.47

owar

-0.46

par

-0.45

味的

-0.45

POSITIVE LOGITS

 coordinates

1.11

 Coordinates

0.99

 position

0.91

 getLocation

0.90

 coords

0.88

 Position

0.86

 location

0.85

 Coord

0.84

 getPosition

0.83

 Positions

0.83

Activations Density 0.269%

keywords related to graphical user interface elements and their manipulation

No Comments

No Known Activations