INDEX

Explanations

mathematical expressions related to optimization choices and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

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

 ngang

-0.42

roveň

-0.41

 yarar

-0.40

[_

-0.40

 gustaría

-0.40

OrNull

-0.40

 yüzden

-0.39

 direct

-0.39

 łą

-0.39

statusText

-0.39

POSITIVE LOGITS

 ModelExpression

0.96

曖昧さ回避

0.94

sizeCache

0.88

\{\\

0.84

PerformLayout

0.83

 propOrder

0.83

rungsseite

0.78

]")]

0.78

verwijspagina

0.75

InputBorder

0.73

Activations Density 1.935%

mathematical expressions related to optimization choices and parameters

No Comments

No Known Activations