INDEX

Explanations

elements related to awards, honors, and biographical publications

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

Efq

-0.90

 itſelf

-0.89

 myſelf

-0.83

 pinulongan

-0.82

 raiſ

-0.80

IVEREF

-0.80

 مرئيه

-0.79

APOLIS

-0.78

ArrowToggle

-0.78

 iNdEx

-0.73

POSITIVE LOGITS

 chân

0.49

penup

0.48

0.44

0.43

il

0.40

 olup

0.40

 beira

0.39

 olisi

0.39

 übernahm

0.38

JsonFormat

0.38

Activations Density 0.905%

elements related to awards, honors, and biographical publications

No Comments

No Known Activations