INDEX

Explanations

references to media content such as TV shows, movies, and associated moments or characters

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

 EconPapers

-0.51

spora

-0.37

oyu

-0.36

ServletRequest

-0.36

 addSubview

-0.36

ArgumentParser

-0.35

logrus

-0.35

)))))

-0.35

 всему

-0.34

POSITIVE LOGITS

RegressionTest

1.14

featureID

0.89

InjectAttribute

0.84

 '\\;'

0.82

 Majefty

0.78

 <>",

0.77

ſelf

0.77

 ویکی‌پدیا

0.77

Efq

0.77

 houſe

0.73

Activations Density 1.074%

references to media content such as TV shows, movies, and associated moments or characters

No Comments

No Known Activations