INDEX

Explanations

mentions of the word "Santa" in various contexts

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

"Santa" followed by a location

np_acts-logits-general · gemini-2.0-flash

santa + place or claus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 مشين

-1.05

makeConstraints

-1.00

Geplaatst

-0.93

ContentAsync

-0.85

 springfox

-0.85

日閲覧

-0.80

出版年

-0.79

PYX

-0.79

 EconPapers

-0.75

@[+][

-0.75

POSITIVE LOGITS

 Santa

0.81

 Claus

0.81

Santa

0.75

SANTA

0.75

Fe

0.74

 SANTA

0.71

 Clause

0.67

 claus

0.64

 santa

0.62

santa

0.61

Activations Density 0.051%

mentions of the word "Santa" in various contexts

"Santa" followed by a location

santa + place or claus

No Comments

No Known Activations