INDEX

Explanations

periods and error-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

SharedDtor

-0.63

 aseg

-0.57

 насељу

-0.55

anskrit

-0.54

 EconPapers

-0.54

?,?,

-0.53

 ویکی‌پدیای

-0.52

inição

-0.51

NameInMap

-0.50

————————————————

-0.50

POSITIVE LOGITS

CloseOperation

0.85

 QtWidgets

0.76

 Elen

0.72

scars

0.71

ברס

0.71

 replays

0.70

VersionUID

0.70

bbene

0.70

ABUL

0.69

iented

0.68

Activations Density 0.170%

periods and error-related terms

No Comments

No Known Activations