INDEX

Explanations

specific references to scientific processes or results in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

الحياه

-0.56

ViewImports

-0.54

BufferException

-0.48

])->

-0.48

 entire

-0.48

">:

-0.47

bottomrule

-0.47

########.

-0.47

">—

-0.47

())));

-0.46

POSITIVE LOGITS

oredCriteria

0.64

posedge

0.64

 månader

0.55

 dagar

0.54

 Secondly

0.54

+#+#

0.53

 دیکھیے

0.53

 Alternatively

0.52

 Bourgoin

0.52

 secondly

0.52

Activations Density 0.551%

specific references to scientific processes or results in documents

No Comments

No Known Activations