INDEX

Explanations

phrases indicating relationships and connections between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.54

on

-0.40

<eos>

-0.39

is

-0.38

-0.37

was

-0.37

 pavimento

-0.35

can

-0.34

 gleichen

-0.34

 were

-0.33

POSITIVE LOGITS

 surla

1.43

 EconPapers

1.26

 disambiguazione

1.16

IntoConstraints

1.10

Portale

1.09

 Roskov

1.08

verwijspagina

1.04

 MainAxisSize

1.04

endphp

1.03

 مشين

1.02

Activations Density 1.334%

phrases indicating relationships and connections between concepts

No Comments

No Known Activations