INDEX

Explanations

mathematical terms and concepts related to linear algebra and statistics

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

Superscript notations like prime, dagger, or transpose

np_acts-logits-general · gemini-2.0-flash

transpose, dagger, adjoint

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

érable

-0.54

 Ains

-0.49

 autoridade

-0.48

acher

-0.46

 AssemblyCulture

-0.46

setCharacter

-0.46

籍

-0.46

 Lazar

-0.45

verdi

-0.45

Ndi

-0.45

POSITIVE LOGITS

 transpose

0.77

transpose

0.76

dagger

0.70

Transpose

0.66

 transposed

0.61

 conjugate

0.60

 CascadeType

0.60

 pylint

0.60

adjoint

0.59

^\

0.59

Activations Density 0.987%

mathematical terms and concepts related to linear algebra and statistics

Superscript notations like prime, dagger, or transpose

transpose, dagger, adjoint

No Comments

No Known Activations