INDEX

Explanations

symbols and notations related to mathematical expressions, particularly in linear algebra and combinatorics

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

Mathematical or logical expressions

np_acts-logits-general · gemini-2.0-flash

indices and sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 متعلقه

-0.59

makeText

-0.55

uzz

-0.50

 doGet

-0.49

getDoctrine

-0.49

ReturnType

-0.48

InputBorder

-0.47

abestanden

-0.46

BASEPATH

-0.46

󠁢

-0.46

POSITIVE LOGITS

0.96

0.91

0.87

0.74

ith

0.67

ｊ

0.63

𝑗

0.63

BagConstraints

0.63

Activations Density 1.942%

symbols and notations related to mathematical expressions, particularly in linear algebra and combinatorics

Mathematical or logical expressions

indices and sequences

No Comments

No Known Activations