INDEX

Explanations

terms related to gangs and criminal activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

NameInMap

-0.62

 propOrder

-0.45

出版年

-0.45

viations

-0.42

PHeader

-0.40

iální

-0.40

 BIRTHDAY

-0.40

 véhicules

-0.39

 <<<<<<<<<<<<<<

-0.39

 vélos

-0.39

POSITIVE LOGITS

 gang

0.73

gang

0.68

gan

0.67

 Gang

0.65

Gan

0.63

Gan

0.60

Gang

0.58

Gun

0.57

Gun

0.56

GAN

0.56

Activations Density 1.720%

terms related to gangs and criminal activity

No Comments

No Known Activations

terms related to gangs and criminal activity

No Comments

No Known Activations