INDEX

Explanations

mathematical expressions and symbols related to matrices and linear algebra

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 condition

-0.48

 worker

-0.46

หาย

-0.45

 AssemblyVersion

-0.44

kach

-0.43

verwijspagina

-0.43

ifoli

-0.43

ệu

-0.42

MoveNext

-0.42

vida

-0.42

POSITIVE LOGITS

 transpose

0.97

transpose

0.75

}^\

0.70

^\

0.69

Transpose

0.69

 transposed

0.66

 transposition

0.65

 AspNetCore

0.64

 TRANSM

0.63

ᵀ

0.60

Activations Density 0.546%

mathematical expressions and symbols related to matrices and linear algebra

No Comments

No Known Activations