INDEX

Explanations

specific numerical patterns or sequences embedded 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 @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 ब्रेकडाउन

-0.54

divia

-0.51

zata

-0.48

 vVar

-0.46

 mence

-0.46

urre

-0.46

DataBind

-0.46

illeurs

-0.46

pano

-0.46

 Dado

-0.45

POSITIVE LOGITS

 myſelf

0.76

IntoConstraints

0.71

اریخ

0.69

 Jefus

0.69

InjectAttribute

0.66

 itſelf

0.65

 inſ

0.64

 ProtoMessage

0.61

 الحره

0.61

 himſelf

0.61

Activations Density 1.200%

specific numerical patterns or sequences embedded in text

No Comments

No Known Activations