INDEX

Explanations

names associated with individuals and their roles or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 himself

-0.63

 Himself

-0.53

himself

-0.49

 נוסף

-0.49

 blow

-0.46

AndGet

-0.46

 הגדול

-0.46

geslacht

-0.45

 inny

-0.45

 Polskiego

-0.43

POSITIVE LOGITS

 ویکی‌پدی

0.60

lorette

0.55

tanleria

0.52

unzel

0.50

NetworkInfo

0.49



0.48

GINIA

0.47

HtmlAttribute

0.47

 zelve

0.47

حياتها

0.46

Activations Density 0.471%

names associated with individuals and their roles or titles

No Comments

No Known Activations