INDEX

Explanations

structured data and references within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 незавершена

-0.77

 autorytatywna

-0.75

 NUKAT

-0.72

 BoxDecoration

-0.65

:✨

-0.60

GeoNames

-0.60

SPATH

-0.59

onAttach

-0.55

DockStyle

-0.55

MENAFN

-0.54

POSITIVE LOGITS

 numbers

0.70

 numeric

0.66

 parseInt

0.66

isNaN

0.64

数字

0.61

 angka

0.60

 chiffre

0.60

數字

0.59

 number

0.58

NSNumber

0.58

Activations Density 0.380%

structured data and references within the text

No Comments

No Known Activations