INDEX

Explanations

assignment operations in programming or data notation

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

Followed by an equals sign

np_acts-logits-general · gemini-2.0-flash

code assignments or variable definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ors

-0.71

–

-0.67

—

-0.62

-0.60

on

-0.59

Rot

-0.58

Se

-0.58

os

-0.58

POSITIVE LOGITS

 ویکی‌پدی

1.38

 esternos

1.12

webElementXpaths

1.10

expandindo

1.09

Дереккөздер

1.08

Vidite

1.06

 itſelf

1.06

Efq

1.02

IsMutable

1.01

 Cæsar

1.01

Activations Density 0.778%

assignment operations in programming or data notation

Followed by an equals sign

code assignments or variable definitions

No Comments

No Known Activations