INDEX

Explanations

mathematical expressions and formulas related to matrices and summation

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

Variables in mathematical expressions

np_acts-logits-general · gemini-2.0-flash

mathematical `j` index

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

Jug

-0.50

Yo

-0.47

Ign

-0.47

Ju

-0.46

варь

-0.44

Yak

-0.44

Ig

-0.43

TestingModule

-0.42

enser

-0.42

FirstResponder

-0.42

POSITIVE LOGITS

2.25

ｊ

1.08

jj

0.95

𝑗

0.92

jent

0.89

jl

0.88

jh

0.85

jand

0.85

jx

0.85

Activations Density 0.573%

mathematical expressions and formulas related to matrices and summation

Variables in mathematical expressions

mathematical `j` index

No Comments

No Known Activations