INDEX

Explanations

mathematical or scientific concepts related to assumptions and models in research

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

abestanden

-0.64

şiv

-0.61

wpi

-0.59

WithIOException

-0.56

DeleteBehavior

-0.56

PyTuple

-0.54

:✨

-0.54

octanol

-0.53

ilem

-0.53

PropertyChanging

-0.52

POSITIVE LOGITS

 برانيه

0.73

forRoot

0.62

UnitTesting

0.60

κτηρισ

0.55

FunctionFlags

0.53

niaus

0.51

 freut

0.49

 freue

0.49

ContextHolder

0.48

 Infórmanos

0.47

Activations Density 2.596%

mathematical or scientific concepts related to assumptions and models in research

No Comments

No Known Activations