INDEX

Explanations

words related to historical events or timelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 فريبيس

-0.55

EndInit

-0.48

iose

-0.46

Ngb

-0.46

PageRoute

-0.45

 benne

-0.43

borderSide

-0.43

RenderAtEndOf

-0.42

Parameteri

-0.42

BlockingQueue

-0.42

POSITIVE LOGITS

<bos>

0.86

ècie

0.75

rawDesc

0.75

 autorytatywna

0.68

 himſelf

0.68

Efq

0.66

>{@

0.65

 Thebes

0.64

dafx

0.63

uanya

0.60

Activations Density 0.970%

words related to historical events or timelines

No Comments

No Known Activations