INDEX

Explanations

positive attributes and evaluations of experiences or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ValueStyle

-0.58

InjectAttribute

-0.51

 chó

-0.45

Mach

-0.45

FXML

-0.43

tampa

-0.42

}]

-0.41

 inade

-0.41

hoff

-0.40

 Enfield

-0.40

POSITIVE LOGITS

AnchorStyles

0.84

abestanden

0.66

ubin

0.62

oa̍t

0.62

 utafitiHapana

0.62

談社

0.59

ARROLL

0.59

kháu

0.59

istration

0.58

vogel

0.57

Activations Density 0.430%

positive attributes and evaluations of experiences or items

No Comments

No Known Activations