INDEX

Explanations

references to the name "Martin," particularly in relation to prominent figures

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

 autorytatywna

-0.74

 Roskov

-0.70

Identyfik

-0.61

InputBorder

-0.60

GIH

-0.57

adaş

-0.57

 astore

-0.57

 '\\;'

-0.56

UGS

-0.56

+#+#

-0.56

POSITIVE LOGITS

 Luther

0.71

 Scorsese

0.70

Anhalt

0.66

Luther

0.56

“……

0.55

elli

0.55

+#+

0.54

eau

0.54

 Marietta

0.54

fsen

0.53

Activations Density 0.110%

references to the name "Martin," particularly in relation to prominent figures

No Comments

No Known Activations