INDEX

Explanations

instances of the term "ha," often indicating laughter or an expression of amusement

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

"ha" or variants, often followed by punctuation

np_acts-logits-general · gemini-2.0-flash

haptic, haunted, haves, hailing, Haithabu

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

Билгалдахарш

-0.59

 MNRAS

-0.55

 Profile

-0.55

osus

-0.54

 wedstrijd

-0.53

ComponentModel

-0.51

 للمعارف

-0.51

onges

-0.50

 rano

-0.50

permanent

-0.50

POSITIVE LOGITS

 <>",

0.59

UnusedPrivate

0.58

 AppCompatTheme

0.57

HtmlAttribute

0.56

 ویکی‌پدیا

0.54

WebServlet

0.52

()?;

0.51

AsUp

0.50

 تضيفلها

0.50

 pylint

0.50

Activations Density 0.121%

instances of the term "ha," often indicating laughter or an expression of amusement

"ha" or variants, often followed by punctuation

haptic, haunted, haves, hailing, Haithabu

No Comments

No Known Activations