INDEX

Explanations

mathematical expressions and parameters related to matrices and dimensions in a context involving data representation

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

Mathematical and matrix notation

np_acts-logits-general · gemini-2.0-flash

dimensions

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 незавершена

-1.07

 ujednoznacz

-0.94

MessageTagHelper

-0.94

 initComponents

-0.89

 дописавши

-0.88

abestanden

-0.85

EndContext

-0.83

 ویکی‌پدیای

-0.82

TagMode

-0.80

 تضيفلها

-0.80

POSITIVE LOGITS

×

1.64

×

1.55

1.47

1.19

by

1.05

×

1.04

×</

0.97

times

0.96

0.95

✕

0.86

Activations Density 0.315%

mathematical expressions and parameters related to matrices and dimensions in a context involving data representation

Mathematical and matrix notation

dimensions

No Comments

No Known Activations