INDEX

Explanations

references to statistical models or frameworks in the context of research studies

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

AxisAlignment

-0.51

opsida

-0.50

 Nautilus

-0.49

省市镇

-0.46

messageInfo

-0.45

rungsseite

-0.44

netics

-0.44

 Steffen

-0.43

følgelig

-0.43

ckså

-0.42

POSITIVE LOGITS

SR

1.33

CR

1.31

SR

1.23

MR

1.22

GR

1.19

DR

1.19

PR

1.18

KR

1.17

CR

1.16

MR

1.14

Activations Density 0.458%

references to statistical models or frameworks in the context of research studies

No Comments

No Known Activations