INDEX

Explanations

phrases related to research findings and conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 presto

-0.38

 dressings

-0.37

 drain

-0.37

 metro

-0.36

appendTo

-0.36

 Garn

-0.36

 nakalista

-0.36

 suppos

-0.36

 simply

-0.36

列

-0.35

POSITIVE LOGITS

 zijne

0.63

BindingResult

0.63

InputBorder

0.62

 <<<<<<<<<<<<<<

0.55

 descubrimiento

0.53

 Unterschiede

0.52

 diferenças

0.51

 verschillen

0.51

UrlResolution

0.50

migrationBuilder

0.50

Activations Density 1.340%

phrases related to research findings and conclusions

No Comments

No Known Activations