INDEX

Explanations

specific legal and medical terminology

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

WriteTagHelper

-0.47

lė

-0.46

LETT

-0.45

 Godfrey

-0.44

backers

-0.44

APTER

-0.44

</tbody>

-0.44

 MERCHANTABILITY

-0.43

 Dang

-0.43

cester

-0.42

POSITIVE LOGITS

ain

0.98

ine

0.97

AIN

0.94

ines

0.90

INE

0.89

in

0.88

ín

0.88

ina

0.87

aine

0.86

EIN

0.84

Activations Density 0.298%

specific legal and medical terminology

No Comments

No Known Activations