INDEX

Explanations

references to awards, recognition, and activism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

-0.89

GEBURTSDATUM

-0.87

 unknownFields

-0.81

NameInMap

-0.81

 EconPapers

-0.81

DoubleQuotes

-0.80

 resourceCulture

-0.80

SBATCH

-0.80

 Мексичка

-0.79

SharedDtor

-0.79

POSITIVE LOGITS

0.44

0.43

х

0.42

ணை

0.41

ModelBuilder

0.41

Cv

0.40

 vini

0.38

0.37

estay

0.37

0.36

Activations Density 5.031%

references to awards, recognition, and activism

No Comments

No Known Activations