INDEX

Explanations

proper nouns related to locations and authority figures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Rtl

-0.49

Rut

-0.45

ga

-0.43

babu

-0.43

SequentialGroup

-0.43

mede

-0.43

astru

-0.42

 Tortoise

-0.42

addSubview

-0.42

 Nintendo

-0.41

POSITIVE LOGITS

Gemeinden

0.71

royd

0.69

 Calder

0.69

 Lancashire

0.68

 Burnley

0.67

 Huddersfield

0.67

󠁢

0.67

:✨

0.66

таратура

0.66

IsMutable

0.66

Activations Density 0.082%

proper nouns related to locations and authority figures

No Comments

No Known Activations