INDEX

Explanations

occurrences of programming-related terminology and function calls

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

Starts with two or three letters

np_acts-logits-general · gemini-2.0-flash

Alpha, MD, ACO, micro

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

GORITHM

-0.60

PRNewswire

-0.59

 further

-0.58

 stay

-0.57

IsContent

-0.54

subpackage

-0.52

LEADING

-0.51

roaches

-0.51

onViewCreated

-0.51

capsulation

-0.50

POSITIVE LOGITS

 مرئيه

0.81

 cherchés

0.73

ſy

0.67

ſelf

0.65

 Diſ

0.64

 Inſ

0.63

outils

0.62

 ſche

0.62

 houſe

0.61

 Reſ

0.60

Activations Density 0.851%

occurrences of programming-related terminology and function calls

Starts with two or three letters

Alpha, MD, ACO, micro

No Comments

No Known Activations