INDEX

Explanations

references to optional data types or fields in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 ویکی‌پدی

-0.49

лтемелер

-0.48

transQ

-0.44

httphttps

-0.44

 IndexPath

-0.43

المناصب

-0.42

Counting

-0.41

 đông

-0.40

 Traffic

-0.39

nsito

-0.39

POSITIVE LOGITS

 float

1.40

float

1.25

 Float

1.14

 parseFloat

1.11

 floats

1.09

 floating

1.08

Float

1.06

FloatField

1.02

 FLOAT

1.00

 floated

0.91

Activations Density 0.626%

references to optional data types or fields in a programming context

No Comments

No Known Activations