INDEX

Explanations

references to specific car models and brands

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Ford Fusion, Motor Co., plant

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 ProtoMessage

-0.64

 jspb

-0.63

MLLoader

-0.61

RegressionTest

-0.60

 surla

-0.56

 المعيارى

-0.55

 Normdatei

-0.53

adhyay

-0.52

reactstrap

-0.52

:✨

-0.52

POSITIVE LOGITS

 Ford

0.41

Ford

0.39

tigte

0.32

 bronco

0.32

 Wege

0.31

 BrowserModule

0.30

 Gladstone

0.29

multicolumn

0.29

SCRIBE

0.29

бурга

0.28

Activations Density 0.051%

references to specific car models and brands

Ford Fusion, Motor Co., plant

No Known Activations