INDEX

Explanations

references to medical professionals and their titles

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

Appears before a name with the title "Dr"

np_acts-logits-general · gemini-2.0-flash

names following dr

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

current

-0.49

 current

-0.48

abrigo

-0.47

 fides

-0.47

 arşivlendi

-0.47

 bloemen

-0.46

อ้างอิง

-0.45

Kjelder

-0.44

 VIDEOTAPE

-0.44

 mắn

-0.43

POSITIVE LOGITS

ummer

0.70

 martens

0.67

 Jekyll

0.65

 صوتيه

0.64

 Seuss

0.64

MarshalTo

0.64

MLLoader

0.62

󠁣

0.61

最快更新

0.60

 Italijanski

0.60

Activations Density 0.074%

references to medical professionals and their titles

Appears before a name with the title "Dr"

names following dr

No Comments

No Known Activations