INDEX

Explanations

commands and actions related to checking, seeing, or visiting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

far

-0.53

in

-0.53

-0.50

 previous

-0.46

-0.44

richter

-0.44

to

-0.43

and

-0.42

 route

-0.42

POSITIVE LOGITS

RegressionTest

1.30

 kasarigan

1.26

 autorytatywna

1.15

 فريبيس

1.12

ValueStyle

1.11

 nahilalakip

1.10

 myſelf

1.10

 AssemblyCulture

1.07

 виправивши

1.03

InputBorder

1.02

Activations Density 0.223%

commands and actions related to checking, seeing, or visiting

No Comments

No Known Activations