INDEX

Explanations

references to matrices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

envolvimento

-0.81

Parcelize

-0.80

 मौ

-0.75

 Unwin

-0.74

 Púb

-0.74

rlrl

-0.70

NewUrlParser

-0.69

бур

-0.67

mord

-0.67

 Pemberton

-0.66

POSITIVE LOGITS

 matrices

1.31

matrices

1.21

 Matrices

1.17

MAT

1.15

MAT

1.14

mat

1.13

 MATRIX

1.13

mat

1.12

MATRIX

1.03

 matrix

1.01

Activations Density 0.227%

references to matrices

No Comments

No Known Activations