INDEX

Explanations

locations and addresses within the context of a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 defaultstate

-0.57

WithMany

-0.50

стма

-0.48

Footnotes

-0.48

 Ajoutez

-0.47

CustomAttributes

-0.46

 հղումներ

-0.45

 transplanting

-0.45

 Quaternion

-0.45

 prem

-0.44

POSITIVE LOGITS

AndEndTag

0.68

出版年

0.65

 resourceCulture

0.53

зулта

0.52

 Nuss

0.52

 himſelf

0.51

🏻

0.50

 Новости

0.50

Архівовано

0.49

Efq

0.49

Activations Density 0.094%

locations and addresses within the context of a narrative

No Comments

No Known Activations