INDEX

Explanations

repeated instances of the word "label" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Читайте

-0.89

")));

-0.79

 />";

-0.78

ſt

-0.76

 Arkivert

-0.75

"]));

-0.75

parsedMessage

-0.74

 Pizarro

-0.74

 Shanks

-0.73

 Stande

-0.73

POSITIVE LOGITS

 label

1.47

 labels

1.46

 Label

1.40

labels

1.34

 Labels

1.34

 LABEL

1.33

Labels

1.28

label

1.24

LABEL

1.21

lbl

1.20

Activations Density 0.057%

repeated instances of the word "label" in various contexts

No Comments

No Known Activations