INDEX

Explanations

punctuation and language constructs related to data representation and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.18.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

RectangleBorder

-0.88

 doInBackground

-0.75

adaptiveStyles

-0.71

InjectAttribute

-0.63

 iſt

-0.63

 whoſe

-0.63

 theſe

-0.63

 onCancelled

-0.61

 raiſ

-0.61

 againſt

-0.60

POSITIVE LOGITS

awtextra

0.69

 Roskov

0.68

 autorytatywna

0.57

DockStyle

0.52

 CreateTagHelper

0.51

 henvisninger

0.49

Referencias

0.45

 patron

0.45

Ha

0.43

利

0.43

Activations Density 0.213%

punctuation and language constructs related to data representation and performance metrics

No Comments

No Known Activations