INDEX

Explanations

numerical data

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

IsContent

-0.79

Estr

-0.60

Datuak

-0.58

 bols

-0.56

 noDo

-0.55

 ----

-0.55

 Biar

-0.54

 Anci

-0.53

 Minha

-0.53

 Mourning

-0.52

POSITIVE LOGITS

 arşivlendi

0.95

 متعلقه

0.74

XmlAccessType

0.72

crollView

0.69

PyExc

0.66

httphttps

0.65

öscht

0.65

reness

0.64

الإنجليزية

0.61

terase

0.61

Activations Density 0.588%

numerical data

No Comments

No Known Activations