INDEX

Explanations

terms related to names and identifiers 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 @ 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

ArrowToggle

-0.86

awtextra

-0.82

ⓧ

-0.78

出版年

-0.76

 noqa

-0.75

twimg

-0.74

 AttributeSet

-0.69

 springfox

-0.69

UpInside

-0.69

Décès

-0.68

POSITIVE LOGITS

bag

0.43

ter

0.43

Ter

0.42

 called

0.41

 sector

0.41

0.40

 term

0.39

cri

0.38

cri

0.38

Zie

0.38

Activations Density 0.609%

terms related to names and identifiers in various contexts

No Comments

No Known Activations