INDEX

Explanations

words and phrases indicating comparison or qualification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Paglinawan

-1.33

 AssemblyCulture

-1.24

GEBURTSDATUM

-1.21

ьаж

-1.18

 surla

-1.13

Personendaten

-1.11

 Signalez

-1.08

RegistryLite

-1.04

 nahilalakip

-1.04

EndGlobalSection

-1.04

POSITIVE LOGITS

 claro

0.47

maß

0.46

нка

0.45

0.44

It

0.40

 This

0.39

‌

0.39

itu

0.38

We

0.36

You

0.35

Activations Density 0.392%

words and phrases indicating comparison or qualification

No Comments

No Known Activations