INDEX

Explanations

terms related to electrical engineering and circuit design

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

Followed by words indicating examples or usage

np_acts-logits-general · gemini-2.0-flash

use and increased

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

—

-0.50

—

-0.50

“

-0.47

-0.44

â

-0.41

–

-0.40

du

-0.39

–

-0.39

POSITIVE LOGITS

tagHelperRunner

1.23

 AssemblyCulture

0.92

NDL

0.90

Jpn

0.90

 purpoſe

0.88

InvalidProtocol

0.88

 ſever

0.88

 uſed

0.86

WebVitals

0.86

 himo

0.85

Activations Density 2.325%

terms related to electrical engineering and circuit design

Followed by words indicating examples or usage

use and increased

No Comments

No Known Activations